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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102091
    Prev
    Next
    INDEX
    Explanations

    I followed by verb

    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
    }$
    -2.06
    嗞
    -1.95
    ↵↵
    -1.84
     pareció
    -1.80
     sorprendió
    -1.71
     decadent
    -1.70
     sabía
    -1.69
    шим
    -1.67
    ！！！
    -1.66
    Siapa
    -1.66
    POSITIVE LOGITS
     we
    2.09
    嘥
    1.94
    commodation
    1.93
    して下さい
    1.91
    翃
    1.88
     hitherto
    1.88
     the
    1.85
    퐿
    1.85
     nasze
    1.83
    玊
    1.80
    Activations Density 0.036%

    No Known Activations