© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8310
    Prev
    Next
    INDEX
    Explanations

    tens digit, 2's complement

    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
     from
    -2.09
     one
    -1.75
     for
    -1.70
    那时
    -1.70
     by
    -1.70
     two
    -1.65
     semacam
    -1.63
     to
    -1.60
    珉
    -1.59
     aún
    -1.57
    POSITIVE LOGITS
    "
    2.14
    </h3>
    1.88
     {
    1.88
     endforeach
    1.80
    утбо
    1.75
     It
    1.74
     pedimos
    1.73
    骉
    1.70
     estaremos
    1.66
    ization
    1.66
    Activations Density 0.023%

    No Known Activations