© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43351
    Prev
    Next
    INDEX
    Explanations

    function, outcome, computer

    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
     So
    -1.63
     Not
    -1.54
     see
    -1.51
     about
    -1.45
     said
    -1.44
    .
    -1.41
     have
    -1.40
     By
    -1.39
    By
    -1.38
    。
    -1.37
    POSITIVE LOGITS
     durer
    1.46
    those
    1.44
     ſet
    1.42
     honden
    1.37
     tomates
    1.35
     suiker
    1.35
    権利
    1.34
    蔔
    1.34
     geel
    1.34
    ième
    1.33
    Activations Density 0.159%

    No Known Activations