© 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. 11676
    Prev
    Next
    INDEX
    Explanations

    bold formatting

    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
    </em>
    0.80
    ahas
    0.74
    นิด
    0.74
    นอก
    0.74
    á
    0.71
    2
    0.69
    ación
    0.69
    ется
    0.68
    og
    0.67
    ahu
    0.67
    POSITIVE LOGITS
    i
    0.81
    在
    0.80
     في
    0.75
    ᆯ
    0.73
    U
    0.72
     در
    0.71
    もら
    0.71
    ၷ
    0.70
    ０
    0.70
    도
    0.68
    Activations Density 0.003%

    No Known Activations