© 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. 71965
    Prev
    Next
    INDEX
    Explanations

    specific words like April and Word

    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
     its
    -1.48
     动物
    -1.40
     harten
    -1.36
     ذلك
    -1.30
     of
    -1.27
     jego
    -1.27
     向け
    -1.26
     siis
    -1.21
     között
    -1.19
     свои
    -1.18
    POSITIVE LOGITS
     there
    1.84
     you
    1.63
     only
    1.43
     lunedì
    1.41
    ↵↵↵
    1.37
     we
    1.36
    +"/
    1.35
     venerdì
    1.35
    𝐃
    1.29
    【
    1.28
    Activations Density 0.124%

    No Known Activations