© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86362
    Prev
    Next
    INDEX
    Explanations

    questions and titles

    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
    (
    -1.87
    一旁
    -1.86
    ࿆
    -1.84
    érape
    -1.80
     продолжа
    -1.77
    曏
    -1.76
     balon
    -1.75
     eşofman
    -1.73
     ortodo
    -1.71
    ѕ
    -1.71
    POSITIVE LOGITS
    ↵
    2.33
     dwóch
    2.14
     abitanti
    1.82
    いただきたい
    1.78
    ୪
    1.75
    ܜ
    1.73
    难以
    1.71
    when
    1.70
     meestal
    1.69
     they
    1.66
    Activations Density 0.002%

    No Known Activations