© 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. 64917
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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_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
     dör
    -0.96
     into
    -0.92
     BECOME
    -0.91
     estreno
    -0.90
     lamang
    -0.90
     Ciências
    -0.87
    eronau
    -0.86
    μένων
    -0.85
    зика
    -0.85
    StateToProps
    -0.84
    POSITIVE LOGITS
    装飾
    0.81
    wikipedia
    0.80
    Sa
    0.80
     fejles
    0.78
     enhancing
    0.77
     hastal
    0.75
    駐車
    0.74
    ks
    0.73
    ido
    0.72
     electronics
    0.72
    Activations Density 0.191%

    No Known Activations