© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 45012
    Prev
    Next
    INDEX
    Explanations

    paths and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    in
    1.39
    of
    1.39
     of
    1.35
     in
    1.33
     to
    1.25
     this
    1.25
    z
    1.20
    ↵
    1.18
    on
    1.18
     the
    1.17
    POSITIVE LOGITS
    跚
    0.80
    とにかく
    0.79
    حيان
    0.77
    respArray
    0.75
    )،
    0.75
    カメラ
    0.74
    隀
    0.73
    เหมือน
    0.72
    resTmp
    0.72
    lių
    0.71
    Activations Density 0.024%

    No Known Activations