© 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. 98556
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
    ↵↵
    -1.13
     then
    -1.06
    iseta
    -1.02
     it
    -0.98
    誹
    -0.98
    cend
    -0.96
     before
    -0.92
     even
    -0.92
    diente
    -0.90
     evidently
    -0.89
    POSITIVE LOGITS
    Pens
    0.96
     deines
    0.96
    WESTERN
    0.94
    jRadioButton
    0.94
    ctxt
    0.90
    綺麗な
    0.90
     habituellement
    0.88
    Ile
    0.88
    无力
    0.87
     milan
    0.87
    Activations Density 0.026%

    No Known Activations