© 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. 123668
    Prev
    Next
    INDEX
    Explanations

    find and determine

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

    techniques explained through steps

    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
     U
    0.50
    รียน
    0.50
    ᄈ
    0.48
     దాని
    0.47
    ِي
    0.47
     its
    0.46
     ល
    0.45
     Arithmetic
    0.45
     SHR
    0.45
     '-':
    0.45
    POSITIVE LOGITS
     opérateur
    0.52
    determine
    0.48
    设定
    0.48
     қай
    0.47
    点は
    0.45
     Vivek
    0.44
     enchanting
    0.44
     espèces
    0.43
     इंजन
    0.43
     eventful
    0.43
    Activations Density 0.000%

    No Known Activations