© 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. 980
    Prev
    Next
    INDEX
    Explanations

    draft followed by document 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
    n
    1.14
    féle
    1.11
    w
    1.11
    im
    1.07
    š
    1.03
    c
    0.99
    r
    0.98
    ți
    0.97
    er
    0.96
    al
    0.96
    POSITIVE LOGITS
    smanship
    1.32
    ין
    1.05
    רים
    1.04
    િંગ
    1.00
    とする
    0.98
    ERS
    0.97
    speople
    0.97
    禇
    0.97
    고자
    0.96
    РИ
    0.93
    Activations Density 0.011%

    No Known Activations