© 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. 118783
    Prev
    Next
    INDEX
    Explanations

    face of, presence of

    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
     in
    -1.77
    隰
    -1.66
     eighty
    -1.61
    埸
    -1.60
     eighteen
    -1.59
     unruly
    -1.59
     Eighty
    -1.57
     eleven
    -1.55
    îte
    -1.54
     eight
    -1.52
    POSITIVE LOGITS
     This
    1.77
     certaines
    1.67
    ⎔
    1.66
    立刻
    1.63
    hidup
    1.61
     både
    1.57
     konkrete
    1.54
    iſter
    1.50
    谡
    1.50
     perfekte
    1.49
    Activations Density 0.017%

    No Known Activations