© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7435
    Prev
    Next
    INDEX
    Explanations

    she/her noun phrases

    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
     himself
    -2.88
     نفسه
    -1.76
     stesso
    -1.48
     mismo
    -1.45
     mücade
    -1.42
     himſelf
    -1.41
     boyhood
    -1.41
     sekarang
    -1.39
    همچنین
    -1.37
    くん
    -1.36
    POSITIVE LOGITS
     herself
    3.17
    athed
    1.93
    dding
    1.55
     her
    1.55
     ее
    1.34
     сама
    1.34
     która
    1.29
     enceinte
    1.29
     miała
    1.27
    helped
    1.27
    Activations Density 2.347%

    No Known Activations