© 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. 112717
    Prev
    Next
    INDEX
    Explanations

    sports, media, health, and demographics

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

    VRAM, system RAM

    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
    daction
    0.49
    兢
    0.47
    葬
    0.47
    daa
    0.47
    弊
    0.46
    而是
    0.45
     සඳ
    0.45
    嘞
    0.45
    參數
    0.45
    jsdel
    0.44
    POSITIVE LOGITS
    '
    0.57
     m
    0.52
     wyd
    0.52
     hou
    0.50
     remaja
    0.50
     mile
    0.49
     minum
    0.49
     kä
    0.48
     dens
    0.48
     hyvä
    0.48
    Activations Density 0.000%

    No Known Activations