© 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. 239930
    Prev
    Next
    INDEX
    Explanations

    download to computer

    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
    +
    0.55
    em
    0.50
    ould
    0.45
    odem
    0.45
    Example
    0.45
    does
    0.44
     academies
    0.44
    re
    0.43
     exemplos
    0.42
    ena
    0.42
    POSITIVE LOGITS
     ንጥረ
    0.59
    кова
    0.57
     расходы
    0.55
    ྗ
    0.54
     Pronghorn
    0.52
     በት
    0.51
     ফেলা
    0.51
     বৃহত্তম
    0.51
     الموقع
    0.51
     використання
    0.51
    Activations Density 0.001%

    No Known Activations