© 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. 109673
    Prev
    Next
    INDEX
    Explanations

    python class

    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
     concussion
    0.46
    Eight
    0.46
    asInstanceOf
    0.43
     Eight
    0.40
    ieuse
    0.40
     eighth
    0.39
     Eau
    0.39
     vacuo
    0.39
    Isaiah
    0.39
    덟
    0.39
    POSITIVE LOGITS
    ពួក
    0.44
     ඔබේ
    0.44
     komun
    0.44
    itektur
    0.44
     kommun
    0.43
     Buscar
    0.43
     대
    0.42
     टेबल
    0.42
     आई
    0.41
     использовали
    0.41
    Activations Density 0.010%

    No Known Activations