© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108352
    Prev
    Next
    INDEX
    Explanations

    OAuth 2.0, OpenID, discovery

    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
    ciosa
    -0.75
    ifun
    -0.72
    🍸
    -0.71
     heredity
    -0.69
     باش
    -0.69
    エリー
    -0.68
     サイ
    -0.68
     Statistic
    -0.68
     współ
    -0.67
     vielfach
    -0.67
    POSITIVE LOGITS
     UserInfo
    1.02
    UserInfo
    0.97
     Discovery
    0.95
    userinfo
    0.91
    Discovery
    0.90
    zé
    0.89
     discovery
    0.87
    discovery
    0.82
    Oid
    0.80
     Rely
    0.79
    Activations Density 0.033%

    No Known Activations