© 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. 45434
    Prev
    Next
    INDEX
    Explanations

    names, brands, or specific entities

    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
     these
    -1.70
    ↵
    -1.66
     richied
    -1.64
     этом
    -1.63
    //{
    -1.46
    ⡯
    -1.46
     этого
    -1.44
     soggior
    -1.43
    </h5>
    -1.41
    nachweise
    -1.40
    POSITIVE LOGITS
     and
    1.70
    了一会儿
    1.52
     (
    1.45
     by
    1.44
    着一
    1.41
    ,
    1.41
    一时间
    1.40
    ;
    1.35
    があります
    1.34
    而后
    1.30
    Activations Density 0.179%

    No Known Activations