© 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. 109315
    Prev
    Next
    INDEX
    Explanations

    whole or part

    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_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
     ทุก
    -0.82
    paravant
    -0.75
     everyone
    -0.73
     kiek
    -0.73
    unless
    -0.71
    みたら
    -0.71
    võ
    -0.71
    ものが
    -0.70
     derselben
    -0.70
    锢
    -0.69
    POSITIVE LOGITS
     whole
    3.06
    whole
    2.55
     partially
    2.47
     wholly
    2.33
    Whole
    2.25
     partly
    2.25
    全
    2.16
     or
    2.09
     Whole
    2.09
     all
    2.08
    Activations Density 0.087%

    No Known Activations