© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109147
    Prev
    Next
    INDEX
    Explanations

    repels, other, water, negatively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_width_262k_l0_small_affine
    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
    1.58
    มี
    1.14
    of
    1.13
    in
    1.09
    จะ
    1.05
    มีความ
    1.04
    ลง
    1.02
    就
    1.02
    ได้
    1.01
    M
    1.01
    POSITIVE LOGITS
     policía
    1.17
     großen
    1.06
    جين
    1.05
     زيد
    1.05
     زين
    1.04
    يد
    1.03
     núcle
    1.03
     кораб
    1.02
    కీయ
    1.02
    ِي
    1.02
    Activations Density 0.000%

    No Known Activations