© 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. 17748
    Prev
    Next
    INDEX
    Explanations

    Enron, Plymouth Colony

    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
    ك
    0.82
    ק
    0.73
     It
    0.71
    मिताभ
    0.70
     Иванович
    0.70
    أ
    0.70
    ిన
    0.69
    ח
    0.69
     Johns
    0.68
     Jeffrey
    0.67
    POSITIVE LOGITS
    on
    1.10
    る
    1.10
    dır
    1.09
    tte
    1.05
    de
    1.01
    '
    0.94
     was
    0.93
    ą
    0.93
    고
    0.92
    t
    0.91
    Activations Density 0.002%

    No Known Activations