© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107248
    Prev
    Next
    INDEX
    Explanations

    TIFF and JPEG image formats

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of the TIFF image format (especially multi-page TIFFs) and related operations (like saving or converting TIFFs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical discussions about raster image files and their software-based handling, such as conversion, compression, rendering, and printing (often in programming or command-line contexts).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical text about image file formats, particularly TIFF and related image processing operations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kent
    -0.77
     Chid
    -0.74
    cliffe
    -0.71
    ź
    -0.70
     אלה
    -0.67
     tentang
    -0.67
    剪
    -0.66
    嵘
    -0.66
     Shield
    -0.66
     shield
    -0.65
    POSITIVE LOGITS
     TIFF
    1.11
     tiff
    1.06
    tif
    1.02
     Tif
    0.95
     tif
    0.93
    TIFF
    0.91
    tiff
    0.87
     resolution
    0.85
     viewers
    0.84
    TIF
    0.82
    Activations Density 0.037%

    No Known Activations