© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    companies, libraries, and models

    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
     ότι
    0.85
     että
    0.81
    І
    0.78
    Р
    0.77
    ബ
    0.74
     ย
    0.73
     bahwa
    0.72
    ،
    0.72
     키
    0.71
     아
    0.70
    POSITIVE LOGITS
    ↵
    1.10
    er
    1.09
    in
    1.02
    る
    0.96
    ל
    0.95
    el
    0.91
    تين
    0.87
    a
    0.86
    تبر
    0.85
    l
    0.83
    Activations Density 0.000%

    No Known Activations