Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8798
    Prev
    Next
    INDEX
    Explanations

    outscored by opponents

    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
     vann
    -0.79
     speł
    -0.77
    ächt
    -0.76
    建て
    -0.75
     alat
    -0.75
    لاش
    -0.75
    حسن
    -0.75
     particularly
    -0.75
    catchError
    -0.75
    ꦼ
    -0.74
    POSITIVE LOGITS
    ;.
    0.91
    __.
    0.85
     Auro
    0.80
    𝖔
    0.79
    ünd
    0.79
     despicable
    0.78
     mui
    0.76
     congru
    0.76
    vw
    0.75
    °.
    0.75
    Activations Density 0.000%

    No Known Activations