© 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. 218260
    Prev
    Next
    INDEX
    Explanations

    multilingual text identification

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

    busy park, sold at, went bankrupt, teeming with

    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
    لیف
    0.50
    推奨
    0.50
    amburg
    0.46
    お手
    0.46
    risome
    0.45
    uoj
    0.44
    hte
    0.43
    輌
    0.43
    inist
    0.43
    cando
    0.43
    POSITIVE LOGITS
    引起
    0.48
     RESPONSE
    0.46
     Clínica
    0.45
    سبة
    0.45
    и
    0.45
     पोस्ट
    0.45
    شي
    0.45
    ERAL
    0.44
     भी
    0.44
     संस्कृति
    0.44
    Activations Density 0.000%

    No Known Activations