© 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. 93699
    Prev
    Next
    INDEX
    Explanations

    licenses and code constructs

    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
     rõ
    -0.77
    ละเอียด
    -0.73
    ('{
    -0.73
    <0xD6>
    -0.68
     miệng
    -0.67
    𝙰
    -0.66
    ваем
    -0.65
     Mother
    -0.65
     بم
    -0.64
     everyday
    -0.63
    POSITIVE LOGITS
    igte
    0.84
    blut
    0.84
    Police
    0.80
    窗外
    0.78
    Ө
    0.75
     Rename
    0.75
    melse
    0.75
     sauté
    0.74
    Shares
    0.74
    rukt
    0.74
    Activations Density 0.045%

    No Known Activations