© 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. 81168
    Prev
    Next
    INDEX
    Explanations

    wargames, recruitment, apps, code

    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
     Convention
    -0.77
     počet
    -0.75
    clero
    -0.72
    strdup
    -0.72
    KELEY
    -0.70
    claves
    -0.70
    listdir
    -0.68
     stroking
    -0.66
    astes
    -0.66
    raz
    -0.66
    POSITIVE LOGITS
     Warhammer
    0.90
    loyee
    0.81
     bí
    0.80
    grim
    0.77
    accu
    0.75
    ubt
    0.75
     gefü
    0.75
     fühlte
    0.73
    detek
    0.73
     entsprechenden
    0.72
    Activations Density 0.004%

    No Known Activations