© 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. 48529
    Prev
    Next
    INDEX
    Explanations

    specific technologies or 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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ønsk
    0.50
     الذ
    0.49
    validacion
    0.49
    <unused1001>
    0.47
    uszt
    0.46
    lesque
    0.46
    czyn
    0.46
     peasantry
    0.46
    म्ह
    0.46
    cké
    0.46
    POSITIVE LOGITS
     geometric
    0.53
     Geometric
    0.49
     geomet
    0.48
    初めて
    0.48
     regular
    0.47
    ’
    0.46
     saturation
    0.44
     creation
    0.44
    ayanti
    0.43
     Gat
    0.43
    Activations Density 0.000%

    No Known Activations