© 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-16K
    7. 12902
    Prev
    Next
    INDEX
    Explanations

    historical or regulatory contexts

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

    just or simply

    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_16k_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
     phospholipids
    0.50
     membrane
    0.46
    單
    0.44
    밸
    0.44
    ल
    0.44
     palatable
    0.44
     fio
    0.43
     ovary
    0.43
     shank
    0.43
     buyer
    0.42
    POSITIVE LOGITS
    ction
    0.48
     زینت
    0.48
    nPortIndex
    0.47
    ựng
    0.45
    }"
    0.45
     ဒါ
    0.44
     これらの
    0.44
    itely
    0.43
    setcounter
    0.42
    stig
    0.42
    Activations Density 0.001%

    No Known Activations