© 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. 8071
    Prev
    Next
    INDEX
    Explanations

    topics, techniques, models

    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
    。
    1.16
    .
    1.13
    ։
    0.98
    se
    0.93
    ak
    0.91
    ។
    0.90
    ’?
    0.89
    ?
    0.89
     curv
    0.88
     pric
    0.88
    POSITIVE LOGITS
    M
    1.25
    B
    1.24
    W
    1.23
    V
    1.18
    K
    1.17
    T
    1.13
    J
    1.13
    N
    1.12
    R
    1.06
    C
    1.04
    Activations Density 0.950%

    No Known Activations