© 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. 65913
    Prev
    Next
    INDEX
    Explanations

    section headers in documentation

    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
    sekten
    -1.12
     når
    -1.07
     других
    -1.06
     作り方
    -1.06
    лением
    -1.05
     Sénat
    -1.05
     інших
    -1.02
     olarak
    -1.02
    uç
    -1.00
    ઃ
    -0.98
    POSITIVE LOGITS
     what
    1.47
     how
    1.19
     who
    1.05
     tía
    1.04
     why
    1.02
     about
    1.02
     situation
    0.98
     schla
    0.98
     where
    0.96
     used
    0.96
    Activations Density 0.106%

    No Known Activations