© 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. 82354
    Prev
    Next
    INDEX
    Explanations

    html input tags and attributes

    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
    聂
    -0.84
    kela
    -0.83
    vní
    -0.79
    」　
    -0.79
    doir
    -0.79
     Starr
    -0.75
    ЖИ
    -0.75
    CharArray
    -0.75
    moc
    -0.75
    …？
    -0.74
    POSITIVE LOGITS
     asp
    1.05
     biasanya
    0.91
    Aantal
    0.90
    Sozial
    0.89
    Rico
    0.89
    shocked
    0.86
    Verein
    0.85
    zwei
    0.84
    ícone
    0.84
     ModelExpression
    0.83
    Activations Density 0.002%

    No Known Activations