© 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-262K
    7. 9640
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and scales

    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_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
     laboratories
    0.48
     quarant
    0.47
     inspectors
    0.46
     attorneys
    0.45
     eras
    0.45
     exhibitors
    0.43
    る
    0.43
     clichés
    0.43
     duplicating
    0.42
     questo
    0.42
    POSITIVE LOGITS
    基础上
    0.54
    ιο
    0.47
    是因為
    0.46
    是因为
    0.44
    িয়ার
    0.43
     圆
    0.41
    йно
    0.41
    లో
    0.40
    isAuthenticated
    0.40
    InnerHTML
    0.40
    Activations Density 0.000%

    No Known Activations