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. 8671
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
     سوخت
    -1.03
     skjø
    -0.88
     seier
    -0.87
     deliberately
    -0.86
     tricky
    -0.85
     gjen
    -0.85
    力の
    -0.84
     unusual
    -0.83
    '});
    -0.83
     fjer
    -0.83
    POSITIVE LOGITS
    from
    1.89
     def
    1.76
    def
    1.73
    import
    1.52
     from
    1.50
     import
    1.29
    elif
    1.27
     از
    1.14
     elif
    1.09
     Python
    1.07
    Activations Density 0.046%

    No Known Activations