© 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. 146728
    Prev
    Next
    INDEX
    Explanations

    si·structure, attacks·happen, drive·up

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

    while avoiding constraints

    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
    させた
    0.47
    れた
    0.46
    鬨
    0.45
     TRIAL
    0.44
     TODAY
    0.44
     burnout
    0.44
     गुम
    0.44
    <0x85>
    0.43
     yachts
    0.42
     Technol
    0.42
    POSITIVE LOGITS
     caderno
    0.54
     :"
    0.51
     einzige
    0.49
     documentos
    0.49
    зка
    0.47
     parserOptions
    0.47
    érez
    0.46
    зки
    0.46
     соблю
    0.46
    冈
    0.46
    Activations Density 0.000%

    No Known Activations