© 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. 10-GEMMASCOPE-RES-131K
    7. 74970
    Prev
    Next
    INDEX
    Explanations

    future possibility

    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
    mitsub
    -1.30
    ciri
    -1.27
    torta
    -1.27
    ,
    -1.26
    迥
    -1.24
     then
    -1.24
    dsquared
    -1.23
     todavía
    -1.18
     his
    -1.17
    remot
    -1.17
    POSITIVE LOGITS
    itisation
    1.52
    lised
    1.45
    cketed
    1.45
    timation
    1.42
    fication
    1.41
     posib
    1.40
    mable
    1.40
    halation
    1.39
    romatic
    1.39
    raisers
    1.38
    Activations Density 0.020%

    No Known Activations