© 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. 41269
    Prev
    Next
    INDEX
    Explanations

    for donation

    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
    ol
    0.57
     l
    0.56
    cida
    0.53
    iva
    0.52
     ao
    0.52
     a
    0.52
     te
    0.51
    (,
    0.51
    ata
    0.50
    olok
    0.50
    POSITIVE LOGITS
     говори
    0.58
    로
    0.56
    ח
    0.56
    Ве
    0.55
    Из
    0.54
    知
    0.54
    지
    0.53
    Р
    0.53
    Б
    0.53
    Эти
    0.52
    Activations Density 0.000%

    No Known Activations