© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59663
    Prev
    Next
    INDEX
    Explanations

    distracted driving

    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
     from
    -1.24
     for
    -1.13
     where
    -1.05
     other
    -1.00
     as
    -0.99
     public
    -0.95
     would
    -0.94
     to
    -0.93
     your
    -0.91
     ±
    -0.90
    POSITIVE LOGITS
    @
    1.45
     @
    1.43
     BASIC
    0.98
    素晴
    0.93
    廡
    0.92
    絶対に
    0.89
    まあ
    0.88
    ↵↵↵↵↵↵↵↵↵↵
    0.88
     at
    0.88
     GUS
    0.88
    Activations Density 0.001%

    No Known Activations