© 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. 143533
    Prev
    Next
    INDEX
    Explanations

    Okay, response structure

    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
     procedimento
    0.51
    готовка
    0.47
     Schulz
    0.47
    ное
    0.46
    -
    0.45
    ные
    0.44
     com
    0.44
    ных
    0.43
     rookie
    0.43
    0.43
    POSITIVE LOGITS
    urkan
    0.50
    ޘ
    0.50
     ٹ
    0.49
    kec
    0.49
    oguć
    0.47
     उच्च
    0.46
    as
    0.46
    iprocal
    0.46
    .”[
    0.46
    杫
    0.46
    Activations Density 0.001%

    No Known Activations