© 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. 118670
    Prev
    Next
    INDEX
    Explanations

    regular season

    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
     Figuren
    -0.80
    ception
    -0.77
     sacrifices
    -0.76
     renforcé
    -0.75
     sereia
    -0.74
     conciertos
    -0.73
     véritable
    -0.72
     herói
    -0.70
    alas
    -0.69
    Waters
    -0.69
    POSITIVE LOGITS
     season
    3.56
    season
    3.17
    Season
    2.70
     Season
    2.58
     SEASON
    2.17
     temporada
    1.99
     saison
    1.81
    シーズン
    1.74
    SEASON
    1.69
     сезон
    1.63
    Activations Density 0.034%

    No Known Activations