© 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. 10-GEMMASCOPE-RES-131K
    7. 100277
    Prev
    Next
    INDEX
    Explanations

    File

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

    the word "File" in programming contexts such as import statements, file paths, and class names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    "
    -3.27
    [
    -3.08
    {
    -2.97
    *
    -2.67
     "
    -2.67
     —
    -2.61
    al
    -2.48
    ly
    -2.38
    ’
    -2.31
    er
    -2.30
    POSITIVE LOGITS
    ⵌ
    2.52
    噲
    2.47
    紲
    2.42
    鏷
    2.42
    渽
    2.42
    ſſen
    2.39
    雳
    2.38
    塍
    2.28
    渌
    2.28
    一阵
    2.28
    Activations Density 0.010%

    No Known Activations