© 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. 41972
    Prev
    Next
    INDEX
    Explanations

    data import and photography

    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
     in
    1.04
    in
    0.95
     and
    0.86
    ial
    0.85
    ing
    0.82
     or
    0.82
    ly
    0.82
    Y
    0.81
     out
    0.80
    ias
    0.78
    POSITIVE LOGITS
    ’
    0.76
    ธ์
    0.67
    用
    0.66
    ’)
    0.65
     raza
    0.65
    ۇل
    0.65
     Lorentzian
    0.65
     consente
    0.64
    that
    0.63
     vatth
    0.63
    Activations Density 0.000%

    No Known Activations