© 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. 22487
    Prev
    Next
    INDEX
    Explanations

    stow, stomp, stoke, stoic

    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
    r
    -2.59
    In
    -2.47
    v
    -2.45
    d
    -2.44
    in
    -2.41
    蜴
    -2.39
    ve
    -2.36
     mistakenly
    -2.28
    te
    -2.25
    en
    -2.22
    POSITIVE LOGITS
    ৹
    2.56
    Ᏹ
    2.56
     gelb
    2.48
    
    2.41
    𐬹
    2.38
    澌
    2.36
     情侣
    2.28
     konkret
    2.25
     você
    2.20
    潆
    2.19
    Activations Density 0.002%

    No Known Activations