© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199213
    Prev
    Next
    INDEX
    Explanations

    seizure came or OK eating

    np_acts-logits-general · gemini-2.5-flash-lite

    contrast or qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     과학
    0.55
    б
    0.54
    Б
    0.52
     सरस्व
    0.51
     பூம
    0.49
     стихо
    0.49
     웨
    0.48
     अलं
    0.48
    ব
    0.47
     치
    0.46
    POSITIVE LOGITS
    zzi
    0.44
     First
    0.40
     Crowd
    0.40
     Kings
    0.39
    且
    0.38
    便是
    0.38
     проведення
    0.37
    )?
    0.37
     ہوں
    0.37
     comenzaron
    0.37
    Activations Density 0.001%

    No Known Activations