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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93253
    Prev
    Next
    INDEX
    Explanations

    exif data and tags

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

    The main thing this neuron does is find references to EXIF metadata (e.g. “exif,” “Exif,” GPS tags, Latitude/Longitude fields, and related commands).

    oai_token-act-pair · o4-miniTriggered 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
     neuropathy
    -0.84
     visuals
    -0.75
     asamblea
    -0.71
    ertor
    -0.69
    Celebrate
    -0.68
    oglu
    -0.67
    elux
    -0.67
    nhold
    -0.66
    esses
    -0.65
    estros
    -0.65
    POSITIVE LOGITS
     EX
    1.82
     metadata
    1.73
    exif
    1.64
     tagging
    1.45
    EX
    1.45
     tags
    1.45
     tagged
    1.40
    metadata
    1.35
     Metadata
    1.34
     IPT
    1.31
    Activations Density 0.060%

    No Known Activations