© 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. 65199
    Prev
    Next
    INDEX
    Explanations

    foreign or similar script

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

    alternative scenarios

    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
    🐁
    0.49
    ={<
    0.48
     Demir
    0.48
    疾
    0.44
    setSelected
    0.44
    🐩
    0.44
     Γ
    0.44
     Δ
    0.43
     renormal
    0.43
     desired
    0.42
    POSITIVE LOGITS
    일본
    0.49
    日本
    0.48
    বস্ত
    0.48
    પ્ર
    0.47
    獨
    0.47
    بية
    0.47
    بین
    0.46
    बिग
    0.46
    戳
    0.46
    杣
    0.46
    Activations Density 0.000%

    No Known Activations