© 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. 10-GEMMASCOPE-RES-131K
    7. 73382
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_10/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
    ↵
    -2.73
    v
    -2.06
    g
    -1.98
    e
    -1.88
    te
    -1.87
    ":
    -1.80
     –
    -1.77
     as
    -1.73
    </h1>
    -1.72
    de
    -1.71
    POSITIVE LOGITS
    during
    2.36
    鲥
    2.13
     следующий
    2.00
    🫃
    2.00
    ⎔
    1.99
    ſch
    1.96
     huile
    1.94
     abstrak
    1.93
     unterkunft
    1.92
    
    1.91
    Activations Density 0.046%

    No Known Activations