© 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. 15488
    Prev
    Next
    INDEX
    Explanations

    often just, relying solely

    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
    硐
    0.43
    ಾಸ
    0.42
    file
    0.42
    ForKey
    0.40
     программа
    0.39
    進
    0.38
    廠
    0.38
    ㈤
    0.38
    لي
    0.38
    ේෂ
    0.38
    POSITIVE LOGITS
     disapproved
    0.54
    ab
    0.46
     archaic
    0.44
    arial
    0.44
     Negev
    0.44
    बो
    0.44
     prese
    0.43
     halved
    0.43
    នឹង
    0.43
    icano
    0.42
    Activations Density 0.000%

    No Known Activations