© 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. 15962
    Prev
    Next
    INDEX
    Explanations

    and/or and related concepts

    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
    ，
    0.78
    ،
    0.64
    $,
    0.57
    О
    0.53
    Хо
    0.52
    Không
    0.50
    』
    0.50
    、
    0.50
    但他
    0.49
    Amount
    0.48
    POSITIVE LOGITS
     have
    0.67
    and
    0.57
     in
    0.55
     gave
    0.55
     took
    0.54
     puso
    0.53
     for
    0.52
     دارای
    0.51
     (!)
    0.51
     The
    0.51
    Activations Density 0.020%

    No Known Activations