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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12250
    Prev
    Next
    INDEX
    Explanations

    code comments and symbols

    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
     in
    -2.14
     on
    -1.88
     one
    -1.84
     at
    -1.79
     as
    -1.77
     not
    -1.74
     two
    -1.69
     had
    -1.63
     through
    -1.58
     most
    -1.57
    POSITIVE LOGITS
     feront
    1.53
    雰囲
    1.49
     déliv
    1.41
     spécialement
    1.39
     Dinas
    1.37
     coloriage
    1.36
     Quando
    1.35
    genodigd
    1.34
     bénéfic
    1.34
    sieur
    1.34
    Activations Density 0.001%

    No Known Activations