© 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. 4356
    Prev
    Next
    INDEX
    Explanations

    linkage criterion

    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
    -
    0.91
    ویه
    0.77
    4
    0.77
    <0x80>
    0.75
    $
    0.75
     domenica
    0.74
    ל
    0.73
    uação
    0.71
     proteção
    0.71
    ４
    0.71
    POSITIVE LOGITS
     in
    1.11
     of
    1.00
    ة
    1.00
    ing
    0.86
    of
    0.79
    在
    0.75
     In
    0.74
     Drs
    0.67
    سل
    0.66
    ات
    0.66
    Activations Density 0.000%

    No Known Activations