© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7377
    Prev
    Next
    INDEX
    Explanations

    evaluating outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    search results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ąg
    0.41
    ReaderWriter
    0.33
    ^{-}$
    0.33
    FhirExtension
    0.32
     തൊ
    0.32
     जीने
    0.32
    ঞ্চ
    0.32
    খানা
    0.31
    勬
    0.31
     ဦး
    0.31
    POSITIVE LOGITS
    結果
    4.63
     results
    4.56
     result
    4.47
    results
    4.38
    结果
    4.38
     resultado
    4.25
     resultados
    4.25
     résultats
    4.22
    result
    4.19
     Results
    4.19
    Activations Density 0.509%

    No Known Activations