© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10835
    Prev
    Next
    INDEX
    Explanations

    style and policy

    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_31_width_65k_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
    ين
    0.79
    dır
    0.73
     buddy
    0.70
    lar
    0.68
    ी
    0.68
     map
    0.66
     candle
    0.65
    る
    0.65
     Bible
    0.65
     GAS
    0.65
    POSITIVE LOGITS
    정책
    0.96
    ۰
    0.95
    政策
    0.93
    policy
    0.91
     정책
    0.88
    Policy
    0.87
    Policies
    0.79
    olicy
    0.77
    ０
    0.77
    POLICY
    0.77
    Activations Density 0.066%

    No Known Activations