© 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. 205685
    Prev
    Next
    INDEX
    Explanations

    speech absolutist

    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
     न्यूयॉर्क
    0.53
    ้
    0.50
     Colombian
    0.47
    heastern
    0.46
    hythmic
    0.46
     ऑस्ट्रेलियाई
    0.45
     Thumbnail
    0.45
     নিউইয়
    0.44
     Finger
    0.43
    งาน
    0.43
    POSITIVE LOGITS
     insinu
    0.50
     resign
    0.48
     voy
    0.48
     pochod
    0.47
    ంతా
    0.45
     repente
    0.45
    J
    0.45
     gelesen
    0.44
     reusing
    0.44
     impuls
    0.43
    Activations Density 0.004%

    No Known Activations