© 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. 7198
    Prev
    Next
    INDEX
    Explanations

    contains things or places

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    梘
    -1.86
    砗
    -1.83
     Filosof
    -1.82
     唯美
    -1.78
    ཋ
    -1.77
     Consumo
    -1.77
    璆
    -1.77
     spørsmål
    -1.76
    魮
    -1.72
     Sosten
    -1.71
    POSITIVE LOGITS
    to
    2.41
    m
    2.34
    //
    2.11
    {
    2.06
     sieben
    2.05
    c
    2.02
    at
    1.95
    1.91
     a
    1.90
    ,’’
    1.88
    Activations Density 0.012%

    No Known Activations