© 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. 31647
    Prev
    Next
    INDEX
    Explanations

    men and women

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

    foreign language terms, sex, economics

    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
    三角形
    0.47
    قان
    0.47
    문
    0.46
    촐
    0.46
    alities
    0.46
    쑤
    0.46
    ᖃ
    0.46
     subfamily
    0.46
     अग
    0.46
    stilling
    0.45
    POSITIVE LOGITS
     τόσο
    0.53
     contrô
    0.48
    itação
    0.46
     Tired
    0.43
     retour
    0.43
     sikk
    0.43
     drunkenness
    0.43
     ruh
    0.42
     tired
    0.42
    帶
    0.42
    Activations Density 0.000%

    No Known Activations