© 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. 22851
    Prev
    Next
    INDEX
    Explanations

    want to be

    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
    祤
    -1.55
     Still
    -1.38
     verbess
    -1.36
     двумя
    -1.34
    IPPI
    -1.29
     "[
    -1.28
    OrCreate
    -1.28
    ..."
    -1.28
     unido
    -1.28
    沨
    -1.27
    POSITIVE LOGITS
     to
    1.67
    </b>
    1.39
    皤
    1.27
    ቍ
    1.16
    gorit
    1.16
     折りたたみ
    1.16
    🢒
    1.15
     getRule
    1.13
     ProtoMessage
    1.09
    休息
    1.08
    Activations Density 0.034%

    No Known Activations