© 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. 541
    Prev
    Next
    INDEX
    Explanations

    attributing quotes

    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
    {
    -2.09
    </em>
    -1.73
    <bos>
    -1.66
     who
    -1.52
     
    -1.38
    ghế
    -1.34
     listos
    -1.31
    ()
    -1.31
     abiertos
    -1.30
     cubiertos
    -1.29
    POSITIVE LOGITS
     in
    2.25
     at
    1.62
    </h1>
    1.52
     становится
    1.47
     That
    1.46
     first
    1.44
     píše
    1.41
     Certainly
    1.40
     boundless
    1.39
    Investi
    1.38
    Activations Density 0.010%

    No Known Activations