© 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. 98649
    Prev
    Next
    INDEX
    Explanations

    dimensions and specifications

    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
    Negative Logits
     it
    -1.66
    3
    -1.43
     erstes
    -1.40
    如同
    -1.37
     SEE
    -1.36
     empezaron
    -1.33
     Бог
    -1.32
     ABSOL
    -1.30
    không
    -1.28
     EACH
    -1.27
    POSITIVE LOGITS
    There
    1.49
     fixa
    1.42
    "),
    1.42
    These
    1.41
    眎
    1.32
     frapp
    1.30
     pursued
    1.28
     palme
    1.27
    塤
    1.27
    "),
    1.26
    Activations Density 0.015%

    No Known Activations