© 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. 165577
    Prev
    Next
    INDEX
    Explanations

    religious state

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

    years, Million, years, newly

    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
    <h2>
    0.58
    قات
    0.53
    <h4>
    0.52
    <h1>
    0.51
    Former
    0.48
    审
    0.48
    Review
    0.47
    审查
    0.47
    <h3>
    0.46
    能
    0.44
    POSITIVE LOGITS
     яичко
    0.48
     क्रमांक
    0.48
     じゃ
    0.47
    ⱼ
    0.46
    Conteudos
    0.45
     microbes
    0.45
     customtkinter
    0.45
     ಬ
    0.45
     trưng
    0.45
    욌
    0.45
    Activations Density 0.003%

    No Known Activations