© 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. 227743
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    ักษณะ
    0.55
    ع
    0.50
    ي
    0.49
    حه
    0.49
    Anyone
    0.48
    حة
    0.47
    يب
    0.46
    ंखला
    0.46
    妘
    0.46
    Heritage
    0.46
    POSITIVE LOGITS
     університету
    0.54
     детям
    0.49
     Nagoya
    0.48
     शुभकामनाएं
    0.48
     GAZ
    0.47
     Ping
    0.47
     어린이
    0.46
     Üniversitesi
    0.46
     παιδιά
    0.46
    idez
    0.46
    Activations Density 0.000%

    No Known Activations