© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23697
    Prev
    Next
    INDEX
    Explanations

    Management of

    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
    НИК
    -0.87
    𝓋
    -0.83
    ując
    -0.83
    kiwa
    -0.82
    jep
    -0.82
    struzioni
    -0.82
     abitanti
    -0.81
     agriculture
    -0.81
    $")
    -0.79
     الشب
    -0.78
    POSITIVE LOGITS
    vertx
    0.88
    0
    0.82
    otes
    0.82
     Vio
    0.77
     liegen
    0.77
    𝑤
    0.77
     Suc
    0.74
     Ganze
    0.74
     vừa
    0.73
    centi
    0.73
    Activations Density 0.003%

    No Known Activations