© 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. 13438
    Prev
    Next
    INDEX
    Explanations

    greeting, ASCII art

    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
    quantile
    0.52
    𝗙
    0.52
    category
    0.50
    ᱖
    0.50
    𝗥
    0.50
    GetOffset
    0.49
    useEffect
    0.49
    elect
    0.48
    facilit
    0.48
    sortTable
    0.48
    POSITIVE LOGITS
     و
    0.60
     it
    0.58
    一个
    0.58
     Kn
    0.57
     a
    0.57
     Poke
    0.57
     It
    0.55
     A
    0.53
     Dove
    0.53
     Hash
    0.53
    Activations Density 0.052%

    No Known Activations