© 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-65K
    7. 31465
    Prev
    Next
    INDEX
    Explanations

    technology and communication tools

    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_31_width_65k_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
    변
    0.45
    母親
    0.44
    增长
    0.44
     الترب
    0.44
     Πε
    0.43
    เจอ
    0.42
    風
    0.41
     적
    0.41
    𝕝
    0.41
    操
    0.40
    POSITIVE LOGITS
    पूर्वक
    0.47
     olmadığını
    0.47
    െയുള്ള
    0.44
     uomini
    0.44
     olmadığı
    0.42
     demokrat
    0.42
    ත්මක
    0.41
    slug
    0.41
    tta
    0.40
    autorisation
    0.40
    Activations Density 0.021%

    No Known Activations