© 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. 38602
    Prev
    Next
    INDEX
    Explanations

    propose to investigate/create/develop

    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
    cún
    -1.59
    •
    -1.48
    all
    -1.45
    垆
    -1.40
    are
    -1.38
     toate
    -1.38
    本当は
    -1.33
    Com
    -1.33
    瑣
    -1.30
     menyebutkan
    -1.27
    POSITIVE LOGITS
    Aktual
    1.30
     opak
    1.30
    ：
    1.28
    焄
    1.27
     latter
    1.27
     appartient
    1.27
    linha
    1.23
    cestors
    1.23
    aabb
    1.23
     её
    1.22
    Activations Density 0.188%

    No Known Activations