© 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. 242692
    Prev
    Next
    INDEX
    Explanations

    female and women

    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
    尊重
    0.44
    拏
    0.41
     THROUGH
    0.40
     stoj
    0.39
     lender
    0.39
     sollten
    0.39
    ٥
    0.38
    stvo
    0.38
    雔
    0.38
     NEVER
    0.38
    POSITIVE LOGITS
     Amalfi
    0.52
    alink
    0.50
     Khao
    0.49
     эффек
    0.49
    Determ
    0.48
     プロ
    0.48
    vocab
    0.48
    ambi
    0.48
    objPHPExcel
    0.47
     лицо
    0.47
    Activations Density 0.001%

    No Known Activations