© 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. 67200
    Prev
    Next
    INDEX
    Explanations

    maaliwalas

    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
    a
    -4.19
    i
    -3.56
    ly
    -3.13
    ro
    -2.97
    <em>
    -2.91
    m
    -2.86
    an
    -2.81
    ा
    -2.77
    い
    -2.70
    ler
    -2.69
    POSITIVE LOGITS
     impeccable
    2.66
     oppose
    2.63
     dwindling
    2.42
    镔
    2.41
    Being
    2.41
    ╿
    2.39
     restructure
    2.36
     якщо
    2.31
     groundbreaking
    2.28
     resolute
    2.27
    Activations Density 0.008%

    No Known Activations