© 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. 99005
    Prev
    Next
    INDEX
    Explanations

    clothing parts, musical terms, object components

    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
    </h3>
    -2.13
    」
    -1.80
    ってみた
    -1.42
    Ꮟ
    -1.41
    tites
    -1.38
    「
    -1.37
    
    -1.31
    ”;
    -1.29
     unele
    -1.29
    "{
    -1.28
    POSITIVE LOGITS
     of
    1.75
     zarówno
    1.66
    vinilo
    1.45
    珦
    1.43
    '
    1.43
    侂
    1.43
     különböző
    1.38
    隳
    1.38
     csapat
    1.36
    𖧵
    1.36
    Activations Density 0.301%

    No Known Activations