© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49860
    Prev
    Next
    INDEX
    Explanations

    unarmed combat or civilians

    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
    Negative Logits
     идти
    0.61
     makeSound
    0.59
     정
    0.59
     condiment
    0.59
     그리고
    0.57
     ferv
    0.57
     방향
    0.57
     ۸
    0.57
     funkci
    0.57
     וא
    0.56
    POSITIVE LOGITS
    ing
    0.89
    and
    0.89
    t
    0.86
    ant
    0.82
    as
    0.80
    at
    0.73
    f
    0.73
    te
    0.73
    '
    0.73
    can
    0.71
    Activations Density 0.000%

    No Known Activations