© 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. 123983
    Prev
    Next
    INDEX
    Explanations

    brands and code preamble

    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
     gelb
    -1.73
    </em>
    -1.69
    
    -1.66
    鉿
    -1.65
    rechter
    -1.63
    葎
    -1.63
     arkiv
    -1.59
    蒾
    -1.59
    ます
    -1.55
    gezogen
    -1.55
    POSITIVE LOGITS
    n
    2.52
    できる
    1.93
    u
    1.85
    '
    1.74
    m
    1.73
    蕷
    1.72
    ;
    1.72
     跡
    1.70
    ate
    1.69
    is
    1.63
    Activations Density 0.004%

    No Known Activations