© 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. 32887
    Prev
    Next
    INDEX
    Explanations

    Object.defineProperty

    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
    ceptibility
    -0.82
     Dokter
    -0.81
     '../../../../
    -0.75
    шек
    -0.75
    Embedding
    -0.72
    kapelle
    -0.72
    SPARENT
    -0.72
    螂
    -0.71
    erex
    -0.71
     pion
    -0.69
    POSITIVE LOGITS
    THF
    0.77
     両
    0.69
    rinks
    0.66
    genstein
    0.65
    休み
    0.65
    ₉
    0.64
    蛤
    0.64
     nên
    0.63
    getBy
    0.63
     protože
    0.63
    Activations Density 0.066%

    No Known Activations