© 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. 210183
    Prev
    Next
    INDEX
    Explanations

    words preceding common follow-ups

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

    taxes and economics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     plástico
    0.47
    скольку
    0.45
    郏
    0.45
    偐
    0.45
     usuário
    0.44
    ibilität
    0.43
    فيد
    0.43
    愊
    0.43
     usuários
    0.42
    jene
    0.42
    POSITIVE LOGITS
     rifles
    0.43
    されない
    0.43
    8
    0.42
     entsteht
    0.40
    られない
    0.40
    ευ
    0.39
    GET
    0.38
     conseils
    0.37
     numeral
    0.37
     secours
    0.37
    Activations Density 0.000%

    No Known Activations