© 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. 219057
    Prev
    Next
    INDEX
    Explanations

    birth parent

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

    where religious or financial matters

    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
    复杂
    0.49
    🆕
    0.48
     admittedly
    0.48
    近年来
    0.48
    日益
    0.48
    全新的
    0.47
    全新
    0.47
     专业
    0.47
     საერთ
    0.46
    芭
    0.46
    POSITIVE LOGITS
     cowardly
    0.69
     delhi
    0.57
     pokemon
    0.52
     dreadful
    0.49
     till
    0.49
     quieres
    0.48
     wala
    0.48
     bacterias
    0.48
     god
    0.47
     firefox
    0.47
    Activations Density 0.000%

    No Known Activations