© 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. 2231
    Prev
    Next
    INDEX
    Explanations

    javadoc tags

    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
     even
    -1.09
    providedIn
    -0.97
    ļi
    -0.96
    Ұ
    -0.94
    ୈ
    -0.91
    ྀ
    -0.89
    おわりに
    -0.88
    \
    -0.87
    kursi
    -0.87
    ඇ
    -0.86
    POSITIVE LOGITS
     @
    2.06
    @
    1.58
    param
    0.93
    ,@
    0.93
    reat
    0.91
     vooral
    0.90
    いい
    0.83
     barricade
    0.82
    non
    0.81
    有时候
    0.81
    Activations Density 0.009%

    No Known Activations