© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210237
    Prev
    Next
    INDEX
    Explanations

    lists and examples

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

    dithering

    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
    Negative Logits
    ンテージ
    0.50
     લઈ
    0.49
     compressible
    0.48
     digestible
    0.48
     théorème
    0.46
    ̀
    0.46
     compressibility
    0.45
     bouch
    0.44
     sắp
    0.44
     使っ
    0.44
    POSITIVE LOGITS
     Sow
    0.51
     authorities
    0.46
     officials
    0.45
    arians
    0.43
    ियमित
    0.43
    evin
    0.43
    Authorities
    0.43
    g
    0.42
    aru
    0.42
     lawyers
    0.42
    Activations Density 0.001%

    No Known Activations