© 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. 237403
    Prev
    Next
    INDEX
    Explanations

    people and their activities

    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
    Clinton
    0.46
    惬
    0.46
    Princeton
    0.46
    故
    0.44
    不由
    0.44
     feest
    0.44
    ツ
    0.44
    偣
    0.44
    ETS
    0.43
    路上
    0.43
    POSITIVE LOGITS
     politicians
    0.50
     politician
    0.48
     resear
    0.47
     articulate
    0.47
     practiced
    0.47
     практику
    0.47
     صرف
    0.46
    characters
    0.46
     practised
    0.46
     دە
    0.46
    Activations Density 0.000%

    No Known Activations