© 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. 10-GEMMASCOPE-RES-131K
    7. 624
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific 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_10/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
    瑒
    -2.81
    等等
    -2.66
     gruppen
    -2.63
     signifikan
    -2.63
     romantis
    -2.61
     praktis
    -2.55
     renk
    -2.52
     peran
    -2.50
     biodivers
    -2.48
     arbe
    -2.45
    POSITIVE LOGITS
    0
    3.70
    *
    2.83
     debuts
    2.69
    続け
    2.45
     делает
    2.45
    茑
    2.41
    lgari
    2.38
    あります
    2.36
    >
    2.36
    裡的
    2.31
    Activations Density 0.031%

    No Known Activations