© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 165981
    Prev
    Next
    INDEX
    Explanations

    religious texts and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privato
    0.43
     criou
    0.42
    Materials
    0.40
    Პ
    0.39
    Education
    0.39
     plików
    0.39
    образова
    0.39
    ファイルの
    0.39
     privati
    0.39
     സൃഷ്ട
    0.38
    POSITIVE LOGITS
     cart
    0.38
    惪
    0.37
     सार
    0.36
     Aleg
    0.36
    煞
    0.36
     Toxic
    0.36
     literal
    0.35
     Revel
    0.35
    arettes
    0.34
     Protective
    0.34
    Activations Density 0.001%

    No Known Activations