© 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. 11433
    Prev
    Next
    INDEX
    Explanations

    date and year ordering

    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
     sabias
    -1.16
     aceptar
    -1.09
    已经
    -1.05
     bocetos
    -1.02
     två
    -1.01
    mayacak
    -0.99
     soportar
    -0.99
     estándares
    -0.98
     spesifik
    -0.97
    也是
    -0.96
    POSITIVE LOGITS
    硯
    1.09
     olympique
    1.05
    mlar
    0.99
    燁
    0.98
     would
    0.98
     imprisoned
    0.98
     prision
    0.96
    保养
    0.96
    autorelease
    0.95
    螢
    0.93
    Activations Density 0.001%

    No Known Activations