© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    foreign language technical terms

    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
     wenn
    -1.04
     dacă
    -1.02
    produktion
    -1.02
    aktion
    -1.01
     nếu
    -1.00
     jeśli
    -0.98
     didn
    -0.97
     известных
    -0.97
     They
    -0.95
    Artículos
    -0.94
    POSITIVE LOGITS
    וּ
    1.14
     меда
    1.12
     Dusche
    1.12
     in
    1.05
     ква
    1.02
     invitamos
    1.01
     спортс
    0.98
    Veranstal
    0.97
     by
    0.97
    varargin
    0.97
    Activations Density 1.520%

    No Known Activations