© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 141667
    Prev
    Next
    INDEX
    Explanations

    paths and shared memory

    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
     שה
    0.72
    すべての
    0.71
     that
    0.70
     creș
    0.68
    シ
    0.68
     and
    0.66
     but
    0.66
    ST
    0.66
    Q
    0.66
     for
    0.63
    POSITIVE LOGITS
    <0xBF>
    0.92
    <0x94>
    0.85
    <0xA0>
    0.82
    <0x9D>
    0.80
    <0xA1>
    0.80
    at
    0.77
    ва
    0.76
    <0x98>
    0.75
    <0xA9>
    0.74
    <0x93>
    0.73
    Activations Density 0.001%

    No Known Activations