© 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. 4867
    Prev
    Next
    INDEX
    Explanations

    debug

    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
    h
    1.61
    är
    1.17
    ography
    1.13
    al
    1.10
    y
    1.09
    -
    1.06
    ing
    1.02
    ,
    0.98
    ij
    0.97
    ili
    0.97
    POSITIVE LOGITS
    ان
    1.57
    ي
    1.39
    ка
    1.38
    ות
    1.35
    ك
    1.34
    м
    1.30
    ма
    1.25
    ла
    1.23
    an
    1.16
    DEBUG
    1.16
    Activations Density 0.010%

    No Known Activations