© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    food dressing and geography

    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
     ਅਤੇ
    0.55
    re
    0.46
     и
    0.46
     grotesque
    0.46
    ן
    0.45
    Α
    0.44
     আৰু
    0.42
     మరియు
    0.42
     וא
    0.42
    和
    0.42
    POSITIVE LOGITS
     (\$
    0.45
     Wichita
    0.44
     कधी
    0.44
    ണ്ടാ
    0.42
     nikdy
    0.42
     called
    0.40
     Typically
    0.40
     baada
    0.40
     Workflow
    0.38
     yaklaşık
    0.38
    Activations Density 0.023%

    No Known Activations