© 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. 72355
    Prev
    Next
    INDEX
    Explanations

    assembly and programming context

    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
     of
    -1.51
    霂
    -1.33
    龊
    -1.29
    」(
    -1.26
    Économie
    -1.25
     pries
    -1.24
    的对象
    -1.23
    钨
    -1.23
    TryDecode
    -1.23
    
    -1.22
    POSITIVE LOGITS
     change
    1.48
    '
    1.37
    Ⲉ
    1.30
    ﾚ
    1.28
     København
    1.28
     inteligente
    1.28
    ༵
    1.27
    琑
    1.26
     pobreza
    1.25
    tième
    1.24
    Activations Density 0.010%

    No Known Activations