© 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. 22-GEMMASCOPE-RES-131K
    7. 33438
    Prev
    Next
    INDEX
    Explanations

    blob data or file paths

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

    The neuron strongly activates on occurrences of the term “blob,” i.e. references to blob data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    氤
    -2.59
    TintMode
    -2.52
    ありますが
    -2.50
    玗
    -2.48
    煐
    -2.48
    哢
    -2.47
     dezelve
    -2.45
    
    -2.45
    镚
    -2.44
    瑆
    -2.39
    POSITIVE LOGITS
    2
    4.09
    '
    3.22
    “
    3.00
    </strong>
    2.98
    1
    2.64
    可以
    2.63
    9
    2.63
    3
    2.61
    *
    2.45
     '
    2.42
    Activations Density 0.006%

    No Known Activations