© 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. 34915
    Prev
    Next
    INDEX
    Explanations

    key-value pairs, or 'over the'

    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
     tested
    -0.70
     rims
    -0.70
    لق
    -0.69
    tión
    -0.68
     light
    -0.68
     Mile
    -0.67
     Colbert
    -0.66
    ėk
    -0.66
    CardView
    -0.66
     free
    -0.66
    POSITIVE LOGITS
    ライプ
    0.75
    址
    0.73
    dba
    0.72
    enance
    0.71
    pulos
    0.66
     בי
    0.65
    ieszka
    0.65
    知
    0.64
     apost
    0.63
    utex
    0.63
    Activations Density 0.060%

    No Known Activations