© 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. 111236
    Prev
    Next
    INDEX
    Explanations

    code and math definitions

    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
    入
    0.52
    Grow
    0.47
    【
    0.46
    小時
    0.46
    住在
    0.46
    Get
    0.45
    Stay
    0.45
    期待
    0.44
    留在
    0.44
    胧
    0.44
    POSITIVE LOGITS
     robbed
    0.48
     pitting
    0.48
     computational
    0.47
     computed
    0.47
     dawned
    0.45
     straightening
    0.45
     usamos
    0.45
     भूषण
    0.45
    idiendo
    0.45
     чек
    0.45
    Activations Density 0.000%

    No Known Activations