© 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. 43532
    Prev
    Next
    INDEX
    Explanations

    (c) copyright

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

    languages, 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
     সম্পূর্ণরূপে
    0.47
    0.46
     során
    0.45
    '।
    0.43
    惰
    0.42
    )。
    0.41
     গুণ
    0.39
     মাধ্যমে
    0.39
     startTime
    0.39
     вали
    0.39
    POSITIVE LOGITS
    작가
    0.54
    ിക്കുക
    0.52
     Issled
    0.49
     Sow
    0.49
    برای
    0.49
     bw
    0.49
     Tonawanda
    0.49
    ਹ
    0.49
    閎
    0.48
    ङ्
    0.48
    Activations Density 0.000%

    No Known Activations