© 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. 118061
    Prev
    Next
    INDEX
    Explanations

    useful information and details

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

    depending on

    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
     militares
    0.52
     های
    0.50
     cualidades
    0.50
     parku
    0.48
    ាប
    0.48
     বৃহৎ
    0.48
    𒍣
    0.48
     größeren
    0.47
     basadas
    0.47
     regiões
    0.47
    POSITIVE LOGITS
    ня
    0.53
    ♋
    0.46
    ма
    0.43
     crowning
    0.43
    <td>
    0.42
     Seafood
    0.42
     способ
    0.41
    autoprefixer
    0.41
    uyền
    0.41
     충
    0.41
    Activations Density 0.001%

    No Known Activations