© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    discussions of benefits

    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
    ı
    1.19
    s
    1.16
    一
    1.15
    ä
    1.13
    ب
    1.11
    ال
    1.06
    ไม่
    1.04
    の
    1.04
    ă
    1.02
    C
    1.01
    POSITIVE LOGITS
    го
    1.06
     beneficios
    1.02
    дка
    0.97
    дная
    0.96
    יה
    0.93
    дят
    0.91
    u
    0.91
    kowe
    0.89
    benefits
    0.87
    де
    0.84
    Activations Density 0.020%

    No Known Activations