© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98606
    Prev
    Next
    INDEX
    Explanations

    get data

    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_34/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
    Took
    -0.79
    Lorenzo
    -0.78
    :+:
    -0.73
    gulation
    -0.70
    _[
    -0.69
     Took
    -0.69
    𝙁
    -0.68
    kopf
    -0.68
    ᴜ
    -0.68
    toa
    -0.67
    POSITIVE LOGITS
    NUC
    0.69
     Yay
    0.66
    nuk
    0.63
     Yosemite
    0.62
     yay
    0.62
    芦
    0.62
    ია
    0.61
    anky
    0.61
     перец
    0.60
     ビッグ
    0.60
    Activations Density 0.074%

    No Known Activations