© 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. 69014
    Prev
    Next
    INDEX
    Explanations

    keyword or proud

    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
    Але
    -0.88
     נוספת
    -0.87
     tồn
    -0.87
    Temporada
    -0.85
    rachtet
    -0.85
    owatt
    -0.85
     Timber
    -0.84
     Secondo
    -0.82
     arbete
    -0.82
    rédients
    -0.81
    POSITIVE LOGITS
     повторя
    0.87
    流れる
    0.81
    我对
    0.79
    стояние
    0.77
     entanglement
    0.74
     повто
    0.73
    yuan
    0.73
     zas
    0.73
     jaką
    0.72
     connected
    0.71
    Activations Density 0.037%

    No Known Activations