© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12004
    Prev
    Next
    INDEX
    Explanations

    man of

    np_acts-logits-general · gemini-2.5-flash-lite

    man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    د
    0.73
    ب
    0.63
    م
    0.63
    ম
    0.60
    リ
    0.58
    as
    0.54
    ER
    0.53
    콜
    0.52
    ام
    0.52
    نا
    0.51
    POSITIVE LOGITS
     man
    0.90
     आदमी
    0.79
     رجل
    0.76
     uomo
    0.76
     hombre
    0.74
     pria
    0.74
    hombre
    0.73
     čovjek
    0.73
     uomini
    0.73
     человеку
    0.71
    Activations Density 0.095%

    No Known Activations