© 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. 26094
    Prev
    Next
    INDEX
    Explanations

    developerwebsite code and configuration

    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
     fik
    0.52
     było
    0.50
     fijo
    0.49
     bylo
    0.49
     gamle
    0.49
    መሳሳይ
    0.49
     série
    0.48
     было
    0.47
    类型
    0.47
    {
    0.46
    POSITIVE LOGITS
    kec
    0.49
    allyl
    0.45
     manifested
    0.44
    ken
    0.43
    BSD
    0.43
    compassing
    0.43
    alf
    0.42
    alih
    0.42
     भुवनेश्वर
    0.41
    brough
    0.41
    Activations Density 0.004%

    No Known Activations