© 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. 8593
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sequences

    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
     as
    -2.34
     or
    -2.17
     if
    -2.03
     now
    -1.87
     use
    -1.69
    <bos>
    -1.56
     you
    -1.55
     which
    -1.54
     is
    -1.49
     occhi
    -1.47
    POSITIVE LOGITS
     zwölf
    1.90
     vielfach
    1.77
     három
    1.77
     тільки
    1.71
     bijna
    1.70
    嘮
    1.68
    cannot
    1.67
    desertcart
    1.65
     peal
    1.65
     éstas
    1.63
    Activations Density 0.004%

    No Known Activations