© 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. 52571
    Prev
    Next
    INDEX
    Explanations

    explaining lists and breakdowns

    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
    0
    0.43
     Experts
    0.42
    Experts
    0.42
     icon
    0.41
     équipes
    0.39
     experts
    0.39
     teams
    0.38
    Captain
    0.38
     heroes
    0.38
     প্রেস
    0.38
    POSITIVE LOGITS
     detain
    0.46
     conclusión
    0.45
     ప
    0.43
     வெவ்வேறு
    0.43
     ප්‍රති
    0.43
     अला
    0.42
    Nw
    0.42
    ្នុង
    0.42
    可能な
    0.42
    運営
    0.42
    Activations Density 0.038%

    No Known Activations