© 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. 13438
    Prev
    Next
    INDEX
    Explanations

    non-profit organization

    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
    by
    0.90
    ри
    0.87
    h
    0.80
    ı
    0.80
    пры
    0.72
    ໂດຍ
    0.71
    س
    0.68
    пь
    0.68
    卫生
    0.67
    POSITIVE LOGITS
    E
    0.74
    šao
    0.72
    K
    0.71
    OL
    0.70
    H
    0.68
    >
    0.65
    ánico
    0.64
    IN
    0.64
    ES
    0.64
    èbre
    0.64
    Activations Density 0.000%

    No Known Activations