© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34321
    Prev
    Next
    INDEX
    Explanations

    collections of data

    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_22/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
    a
    -1.57
    ↵↵
    -1.55
    *
    -1.51
    It
    -1.44
     ;
    -1.38
    \
    -1.38
      
    -1.30
     .
    -1.26
     )
    -1.22
     They
    -1.22
    POSITIVE LOGITS
    樯
    1.48
    舢
    1.39
    瞽
    1.30
    屺
    1.30
     harde
    1.29
     comparten
    1.28
    衚
    1.28
     continúas
    1.28
    쏙
    1.27
     plancher
    1.26
    Activations Density 0.003%

    No Known Activations