© 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. 82668
    Prev
    Next
    INDEX
    Explanations

    scaling factors like 3x

    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
     also
    -1.67
     authService
    -1.05
     neither
    -1.05
    ,
    -0.98
     either
    -0.96
    .
    -0.93
     not
    -0.92
     an
    -0.90
     often
    -0.88
     even
    -0.87
    POSITIVE LOGITS
    كويكب
    1.14
     flera
    1.02
     ۲۰۰
    0.99
     *++
    0.97
     مرور
    0.96
    ̀u
    0.95
    wesenheit
    0.92
    ジア
    0.92
    nalités
    0.91
    帰る
    0.91
    Activations Density 0.008%

    No Known Activations