© 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. 34-GEMMASCOPE-RES-131K
    7. 57304
    Prev
    Next
    INDEX
    Explanations

    typesetting characters, punctuation

    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
     goederen
    -0.85
    dcmdata
    -0.82
    getLabel
    -0.77
     Edges
    -0.77
    ыре
    -0.75
    tinggi
    -0.75
     diatas
    -0.75
    úi
    -0.74
     hdr
    -0.74
    тием
    -0.73
    POSITIVE LOGITS
     literary
    1.09
    Literary
    0.97
     фоне
    0.95
     punctuation
    0.93
    literary
    0.92
     Literary
    0.91
     gram
    0.89
     literacy
    0.89
     Character
    0.85
    character
    0.84
    Activations Density 0.032%

    No Known Activations