© 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. 8497
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
     on
    0.72
    c
    0.66
     for
    0.65
    for
    0.64
    and
    0.63
    p
    0.62
     or
    0.61
     and
    0.61
    k
    0.60
    이
    0.59
    POSITIVE LOGITS
    -
    0.75
    .
    0.74
    <0xBE>
    0.69
    :
    0.68
    <0xBB>
    0.60
    <0xB2>
    0.58
    <0x87>
    0.57
    (
    0.57
    3
    0.57
    <0xAB>
    0.56
    Activations Density 0.049%

    No Known Activations