© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6402
    Prev
    Next
    INDEX
    Explanations

    statement and its context

    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_16_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
     (
    1.36
     -
    1.32
     to
    1.26
    -
    1.17
    ,
    1.08
    ión
    1.05
     '
    1.04
    dır
    1.04
    แต่
    1.04
    ۳
    1.02
    POSITIVE LOGITS
    for
    1.04
    on
    1.03
    ти
    0.99
    ین
    0.99
    (',');
    0.95
    不
    0.95
    onOptions
    0.94
    ర్
    0.91
     finalizar
    0.91
    ంగ్‌
    0.91
    Activations Density 0.321%

    No Known Activations