© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85289
    Prev
    Next
    INDEX
    Explanations

    referring to a male individual

    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
    ↵↵
    -3.92
    “
    -3.22
    、“
    -2.73
    ，“
    -2.73
    .”
    -2.69
    ”
    -2.61
    ureux
    -2.53
    鴣
    -2.52
    霙
    -2.41
    。“
    -2.39
    POSITIVE LOGITS
     It
    3.80
     ‘‘
    2.64
    1
    2.52
    というわけで
    2.31
     WITH
    2.28
    有一個
    2.27
    させて頂きます
    2.27
     BEFORE
    2.19
    Ndr
    2.19
     to
    2.14
    Activations Density 0.101%

    No Known Activations