© 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. 29388
    Prev
    Next
    INDEX
    Explanations

    said, multilingual speech markers

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

    Intelligence and context

    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
     الخلف
    0.58
     裏
    0.50
    mck
    0.50
     সহজে
    0.48
    मिताभ
    0.47
     大き
    0.47
     Frem
    0.46
     কেন্দ
    0.46
     항목
    0.46
    迅速
    0.46
    POSITIVE LOGITS
    إن
    0.54
     said
    0.48
     pé
    0.47
     dye
    0.46
     kaka
    0.46
    由
    0.45
     slay
    0.44
    ت
    0.44
    ש
    0.44
    said
    0.44
    Activations Density 0.000%

    No Known Activations