© 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. 248428
    Prev
    Next
    INDEX
    Explanations

    Arabic words and proper nouns

    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
     완
    0.48
    并未
    0.47
     Поскольку
    0.47
     마찬가지
    0.46
     허
    0.46
    比亚
    0.46
     spectroscopy
    0.45
     سعودی
    0.45
     보안
    0.45
     뭔
    0.45
    POSITIVE LOGITS
    ov
    0.52
    يس
    0.49
    is
    0.48
    ويل
    0.48
    ونس
    0.48
    l
    0.47
    ូច
    0.47
    els
    0.46
    Description
    0.46
    Computer
    0.46
    Activations Density 0.000%

    No Known Activations