© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109931
    Prev
    Next
    INDEX
    Explanations

    code keywords like using and define

    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
     て
    -0.76
     defekt
    -0.76
     leves
    -0.75
     diverses
    -0.75
     Lite
    -0.75
     potency
    -0.74
     EXCEPT
    -0.74
    λοι
    -0.74
     aplicada
    -0.74
    τό
    -0.73
    POSITIVE LOGITS
     eliminare
    0.73
    仕事の
    0.72
     gestorben
    0.70
     пак
    0.70
    スピード
    0.66
    遊ぶ
    0.66
    本当の
    0.65
     rhymes
    0.65
     gedaan
    0.65
    レシピ
    0.64
    Activations Density 0.003%

    No Known Activations