© 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-16K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    query, task, problem, object type

    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_16k_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
     be
    0.86
    قة
    0.75
    <0x80>
    0.72
    ել
    0.68
    ного
    0.66
    重视
    0.65
     zwe
    0.64
    妽
    0.63
    үй
    0.62
     inté
    0.62
    POSITIVE LOGITS
    ac
    0.96
    ’
    0.94
    로
    0.93
    aka
    0.86
    i
    0.77
    ran
    0.76
    ?}
    0.75
    other
    0.75
    cc
    0.74
    ir
    0.74
    Activations Density 0.135%

    No Known Activations