© 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. 247812
    Prev
    Next
    INDEX
    Explanations

    dates, specific, foreign languages

    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
     Texans
    0.48
    ح
    0.46
    ါ
    0.46
    ាក
    0.45
     restable
    0.44
    opies
    0.43
    از
    0.43
    اي
    0.43
    ي
    0.43
     Tex
    0.41
    POSITIVE LOGITS
     음식
    0.48
     소녀
    0.48
     특정
    0.47
     tanggal
    0.47
     विहार
    0.46
    츤
    0.46
    عنی
    0.46
     diesen
    0.46
     знаете
    0.46
     તેથી
    0.46
    Activations Density 0.000%

    No Known Activations