© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    diverse groups, specific demographics

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

    exploring beyond power dynamics

    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
    之类的
    0.50
    的意思
    0.49
    writeToFile
    0.47
    投注
    0.45
     或者
    0.45
    randomNumber
    0.44
    ﺩ
    0.44
    ｨ
    0.44
    ScriptAssemblies
    0.44
    Datei
    0.44
    POSITIVE LOGITS
     LGBTQ
    0.74
     beyond
    0.69
     transgender
    0.68
     दिव्यांग
    0.67
     Tibetan
    0.64
     non
    0.64
     inclusiv
    0.64
     Beyond
    0.64
     pediatric
    0.63
     Women
    0.63
    Activations Density 0.017%

    No Known Activations