© 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. 11377
    Prev
    Next
    INDEX
    Explanations

    same or still

    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
     cieka
    -1.02
    Então
    -0.95
    tarjeta
    -0.93
    prettier
    -0.90
     modernas
    -0.88
    Quiénes
    -0.88
     belki
    -0.88
    ETERS
    -0.87
    комплект
    -0.87
     sogenannten
    -0.86
    POSITIVE LOGITS
     same
    1.84
    same
    1.60
     still
    1.46
    still
    1.39
    Same
    1.38
     mêmes
    1.34
     همان
    1.30
     trademark
    1.29
    依旧
    1.23
     vẫn
    1.22
    Activations Density 0.056%

    No Known Activations