© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11404
    Prev
    Next
    INDEX
    Explanations

    function and variable definitions

    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
     igen
    -1.21
     Jego
    -1.09
    Gdzie
    -1.03
     lider
    -1.02
     ot
    -1.02
     salari
    -0.97
     otra
    -0.94
    BuildConfig
    -0.93
     serta
    -0.93
     flaming
    -0.93
    POSITIVE LOGITS
     însă
    1.48
     uusi
    1.31
     però
    1.28
      [
    1.23
     ajoute
    1.22
     geralmente
    1.20
     ajudar
    1.17
     však
    1.16
     ciertas
    1.16
    plona
    1.16
    Activations Density 0.010%

    No Known Activations