© 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. 31-GEMMASCOPE-2-RES-262K
    7. 225628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     произведение
    0.44
    部門
    0.43
     spindles
    0.42
    졔
    0.42
     Polaribacter
    0.42
    子女
    0.40
     ছেড়ে
    0.40
    ଝ
    0.40
    ྥ
    0.39
     drowsiness
    0.39
    POSITIVE LOGITS
    et
    0.60
    ed
    0.57
    rid
    0.56
    un
    0.54
    es
    0.53
    as
    0.52
    ad
    0.52
    idem
    0.52
     ibid
    0.49
    meye
    0.48
    Activations Density 0.003%

    No Known Activations