© 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. 22-GEMMASCOPE-RES-131K
    7. 9674
    Prev
    Next
    INDEX
    Explanations

    names and descriptive words

    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_22/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
    rı
    -1.12
     männis
    -1.05
    fähig
    -1.03
     metus
    -1.03
     міся
    -1.03
    iseerd
    -1.00
    وذ
    -0.96
    ële
    -0.96
    thodon
    -0.96
    carboxylic
    -0.94
    POSITIVE LOGITS
     said
    1.09
     ativar
    1.09
     höl
    1.06
     didn
    1.05
    他說
    1.04
     område
    1.03
     złotych
    1.02
     wasn
    1.01
     plaît
    1.00
    ズル
    0.99
    Activations Density 0.018%

    No Known Activations