© 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. 83298
    Prev
    Next
    INDEX
    Explanations

    blue case

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

    seconds

    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
     危
    0.40
     diplomas
    0.40
     মেয়ের
    0.39
     dipl
    0.38
     六
    0.38
     一个
    0.37
     大学
    0.37
    ippy
    0.36
     costumes
    0.36
     aplikasi
    0.36
    POSITIVE LOGITS
    궜
    0.41
    례
    0.40
    प्रदेश
    0.40
    readlines
    0.38
     ambao
    0.37
    फिया
    0.36
    嘖
    0.35
    કર
    0.35
    idão
    0.35
    କ
    0.35
    Activations Density 0.055%

    No Known Activations