© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 2203
    Prev
    Next
    INDEX
    Explanations

    conjunctions or separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    δια
    0.35
    LOL
    0.34
    دی
    0.33
    Έ
    0.33
    比如
    0.33
     例如
    0.32
    например
    0.32
    ?,?,
    0.32
    CB
    0.32
     توی
    0.32
    POSITIVE LOGITS
     and
    0.78
     vs
    0.78
     versus
    0.77
     ಮತ್ತು
    0.75
     आणि
    0.72
     અને
    0.72
     và
    0.70
     и
    0.68
     ও
    0.68
     மற்றும்
    0.68
    Activations Density 0.208%

    No Known Activations