© 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. 66069
    Prev
    Next
    INDEX
    Explanations

    code syntax headers and keywords

    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
    ്ട
    -2.44
    
    -2.34
     meskipun
    -2.34
    鬭
    -2.19
    dersfield
    -2.19
     meski
    -2.19
    zają
    -2.14
    ophageal
    -2.11
     jepang
    -2.09
     setelah
    -2.08
    POSITIVE LOGITS
    ↵
    2.42
     
    2.36
    ,
    2.23
     &
    2.22
    e
    2.05
    !
    1.94
    -
    1.90
     And
    1.90
    m
    1.89
     …
    1.87
    Activations Density 0.027%

    No Known Activations