© 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. 127772
    Prev
    Next
    INDEX
    Explanations

    biggest single

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

    store creation, with caveats, world record

    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
    ઢી
    0.44
    弐
    0.44
    巻き
    0.43
    timepoint
    0.43
    কাঁ
    0.43
    Lf
    0.43
    蓮
    0.43
    minutes
    0.43
    Didn
    0.43
    ંદા
    0.43
    POSITIVE LOGITS
     但
    0.66
     contre
    0.53
     but
    0.52
     الأز
    0.52
    4
    0.51
     arasındaki
    0.50
    额
    0.50
     christ
    0.50
     对
    0.49
     pendant
    0.49
    Activations Density 0.001%

    No Known Activations