© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36887
    Prev
    Next
    INDEX
    Explanations

    message problems starts visual

    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
    id
    0.46
    n
    0.42
     ent
    0.42
    user
    0.41
    స్తు
    0.40
     Fan
    0.40
    భ్య
    0.40
    u
    0.40
    דע
    0.40
    per
    0.40
    POSITIVE LOGITS
     ഉണ്ടായി
    0.56
     ছিল
    0.55
     இல்லாமல்
    0.55
     scrittura
    0.54
     żad
    0.54
    andosi
    0.53
     chiamato
    0.53
    CONFLICT
    0.52
    NUCLEAR
    0.52
    PERTY
    0.51
    Activations Density 0.009%

    No Known Activations