© 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. 135314
    Prev
    Next
    INDEX
    Explanations

    Yellow, dB, grey

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Barbie
    0.53
    ’
    0.49
     tant
    0.44
     Karate
    0.43
    <0xE3>
    0.43
    1
    0.43
    <i>
    0.42
    わせ
    0.42
     jeune
    0.42
     Tant
    0.42
    POSITIVE LOGITS
    ్య
    0.49
    gaxModule
    0.48
    ಟರ್
    0.46
    𒂠
    0.46
    Customize
    0.43
    ್ಯ
    0.43
     μεγ
    0.43
    Endpoints
    0.43
    iterranean
    0.43
     characterize
    0.42
    Activations Density 0.008%

    No Known Activations