© 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. 12215
    Prev
    Next
    INDEX
    Explanations

    Category lists

    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
     with
    -1.79
     putting
    -1.66
     through
    -1.66
     as
    -1.63
     With
    -1.55
     at
    -1.52
     From
    -1.51
     their
    -1.51
     for
    -1.50
     by
    -1.48
    POSITIVE LOGITS
    訁
    1.68
     offrent
    1.64
     AMAZING
    1.59
     REALLY
    1.54
     fonctionnent
    1.52
     blatant
    1.50
     sélectionnés
    1.48
     fanatic
    1.45
    轳
    1.44
     consommer
    1.42
    Activations Density 0.003%

    No Known Activations