© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68480
    Prev
    Next
    INDEX
    Explanations

    punct, prophecy, 'agua', 'Ying', 'Amos'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doesnt
    -2.61
    
    -2.28
    銥
    -2.28
     precisamos
    -2.27
    蕺
    -2.22
    —
    -2.22
    ſelves
    -2.22
    ного
    -2.19
     isnt
    -2.17
     Répondre
    -2.17
    POSITIVE LOGITS
    '
    3.67
    ໊
    2.66
    噠
    2.52
    哏
    2.50
    linawan
    2.42
    詼
    2.38
    "
    2.38
    嘍
    2.33
     jeder
    2.30
     главный
    2.28
    Activations Density 0.003%

    No Known Activations