© 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. 43822
    Prev
    Next
    INDEX
    Explanations

    utility when

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

    Masonic symbolism

    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
     speakers
    0.40
    狸
    0.39
    šnj
    0.39
     geschikt
    0.39
     продажи
    0.38
     fiyat
    0.38
    售价
    0.37
     SDW
    0.37
     đừng
    0.37
    峰
    0.37
    POSITIVE LOGITS
     множество
    0.47
    🍂
    0.47
    📋
    0.45
    ሠ
    0.44
    🍲
    0.44
    들에게
    0.44
     debilitating
    0.44
    ln
    0.44
    🟧
    0.43
     ஆயிர
    0.43
    Activations Density 0.000%

    No Known Activations