© 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. 79723
    Prev
    Next
    INDEX
    Explanations

    noun of noun/pronoun

    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
    okości
    -0.97
     précédents
    -0.94
    誰
    -0.93
     suavemente
    -0.90
     Danh
    -0.90
    Abraços
    -0.88
    PQ
    -0.86
    enne
    -0.86
     cómod
    -0.85
     húmedo
    -0.85
    POSITIVE LOGITS
     in
    1.30
     on
    1.08
     as
    1.01
     during
    0.91
    されています
    0.90
    гляд
    0.89
     rurale
    0.88
    といった
    0.85
    性を
    0.84
     тоже
    0.84
    Activations Density 0.223%

    No Known Activations