© 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. 44341
    Prev
    Next
    INDEX
    Explanations

    scientific notation and exponents

    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
    that
    -1.56
     That
    -1.52
     PartialEq
    -1.48
     but
    -1.44
     BorderLayout
    -1.38
    whose
    -1.37
     Such
    -1.34
     grosse
    -1.32
     He
    -1.31
     זיי
    -1.31
    POSITIVE LOGITS
    0
    1.52
     сказала
    1.42
     naszych
    1.41
     wydaje
    1.35
     мы
    1.34
     üblichen
    1.33
    colgante
    1.30
     bewertet
    1.29
     angefangen
    1.29
     pidió
    1.28
    Activations Density 0.056%

    No Known Activations