© 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. 35801
    Prev
    Next
    INDEX
    Explanations

    specific nouns and clauses

    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
    URIDAD
    -1.01
     بيها
    -0.92
     ソファ
    -0.85
    gewiesen
    -0.85
     couvrir
    -0.85
     يت
    -0.84
    어
    -0.83
    지
    -0.83
     тут
    -0.82
     sitä
    -0.82
    POSITIVE LOGITS
     and
    0.99
     laim
    0.95
    逡
    0.93
    tuvo
    0.93
     ۱۴
    0.91
    ؼ
    0.91
    ✂
    0.90
    詣
    0.90
    睨
    0.89
    💓
    0.89
    Activations Density 0.107%

    No Known Activations