© 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-262K
    7. 4302
    Prev
    Next
    INDEX
    Explanations

    preceded by 'max', 'min', 'size', 'diameter', 'view', 'appendChild', 'name', 'empty'

    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_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
    }$=
    0.33
    危机
    0.33
    战争
    0.31
    Kaynak
    0.31
     프랑
    0.30
    Neces
    0.30
    ഒരു
    0.30
    情報
    0.29
     പോലുള്ള
    0.29
    ૄ
    0.29
    POSITIVE LOGITS
    ↵
    0.37
     to
    0.32
     I
    0.31
     by
    0.31
    -
    0.31
     of
    0.30
     said
    0.30
    _
    0.30
     final
    0.30
     on
    0.29
    Activations Density 1.127%

    No Known Activations