© 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. 200091
    Prev
    Next
    INDEX
    Explanations

    بسم اللّٰه

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

    names, concepts, concerns, websites

    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
    鍗
    0.51
     設定
    0.49
     रिश्वत
    0.49
     कॅम्प
    0.48
    leni
    0.45
     ProRes
    0.45
     Camden
    0.45
     ಮಾರ
    0.45
    緝
    0.45
     ডাকা
    0.44
    POSITIVE LOGITS
    ك
    0.61
    كَ
    0.50
    كا
    0.46
    ظ
    0.46
    voud
    0.46
    بسم
    0.45
    ","#
    0.44
    الإ
    0.44
    waż
    0.44
    ,#
    0.44
    Activations Density 0.001%

    No Known Activations