© 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. 176748
    Prev
    Next
    INDEX
    Explanations

    people aren't

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

    code blocks and lists

    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
    ARD
    0.54
    aircraft
    0.50
     ホ
    0.48
    shelf
    0.46
    FORM
    0.46
    mUserManager
    0.46
    attr
    0.46
    +</
    0.45
     米
    0.45
    maximum
    0.44
    POSITIVE LOGITS
     क्रिया
    0.54
     dicion
    0.51
     सांस
    0.50
     कोड
    0.50
     ocasion
    0.49
     kumpulan
    0.48
    ገባ
    0.48
    ន្ល
    0.48
     امشي
    0.48
     ejecución
    0.47
    Activations Density 0.000%

    No Known Activations