© 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. 74704
    Prev
    Next
    INDEX
    Explanations

    underlying, driven, acceleration, purity

    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
    Scenic
    0.47
    洷
    0.46
    咳
    0.45
     conexão
    0.45
     ومد
    0.44
     कने
    0.44
     कनेक्शन
    0.43
     forbindelse
    0.42
    𒈠
    0.42
     ან
    0.41
    POSITIVE LOGITS
     Keychain
    0.49
     keychain
    0.46
    raint
    0.44
     who
    0.43
    ケーション
    0.43
    itä
    0.43
     fluctu
    0.41
     [];
    0.41
    agues
    0.41
    ptides
    0.40
    Activations Density 0.003%

    No Known Activations