© 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. 80301
    Prev
    Next
    INDEX
    Explanations

    and stable

    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
     الهمزه
    0.43
     Prensa
    0.43
    ਕ
    0.43
     znovu
    0.42
     vollständ
    0.42
     avanzar
    0.42
     Consulate
    0.42
     الكامل
    0.41
    ريب
    0.41
    批
    0.41
    POSITIVE LOGITS
     paintball
    0.46
     tyres
    0.46
     (
    0.45
     τ
    0.44
     ş
    0.43
     paint
    0.42
     tyre
    0.42
     ш
    0.42
     courses
    0.41
     railing
    0.41
    Activations Density 0.002%

    No Known Activations