© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64026
    Prev
    Next
    INDEX
    Explanations

    code declarations: public, function, const, export

    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
    /**
    -2.14
    /**
    -1.48
    ///
    -1.27
     -
    -1.16
     it
    -1.16
    <blockquote>
    -1.13
    !!!
    -1.12
     ${
    -1.06
    """
    -1.04
     /**
    -1.04
    POSITIVE LOGITS
     podla
    1.01
    
    0.98
    МА
    0.98
     рассчиты
    0.98
    votre
    0.98
    länger
    0.97
     Achieve
    0.97
    pecabe
    0.96
     AVOID
    0.96
    avait
    0.96
    Activations Density 0.009%

    No Known Activations