© 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. 126140
    Prev
    Next
    INDEX
    Explanations

    단위/개수/횟수/단계

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

    multi-lingual inputs

    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
    對於
    0.54
    াদনের
    0.53
    ‶
    0.52
    內的
    0.50
    പാടി
    0.50
    对于
    0.49
    ጆች
    0.48
    ्याम
    0.46
     einiger
    0.46
    ための
    0.45
    POSITIVE LOGITS
    ~
    0.49
     sayıda
    0.48
     होने
    0.47
     режим
    0.47
    으로
    0.46
     সংখ্যক
    0.45
    리로
    0.43
    மையாக
    0.43
    E
    0.43
    이라고
    0.42
    Activations Density 0.006%

    No Known Activations