© 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. 57482
    Prev
    Next
    INDEX
    Explanations

    following conditions

    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
    Также
    -0.89
     function
    -0.84
    災
    -0.82
    addPreferredGap
    -0.81
    痪
    -0.81
    final
    -0.80
     Bute
    -0.79
    function
    -0.79
    уре
    -0.79
     występu
    -0.77
    POSITIVE LOGITS
    klik
    0.93
    MUM
    0.91
    رسی
    0.82
     ()
    0.81
     !_
    0.81
    ımıza
    0.80
    тего
    0.77
     chargée
    0.77
     Valores
    0.77
     fysis
    0.77
    Activations Density 0.001%

    No Known Activations