© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130131
    Prev
    Next
    INDEX
    Explanations

    numerical and geometric values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     각각
    0.47
    ಿವೆ
    0.42
     तीनों
    0.39
    󠁧
    0.39
    Gosudarstvennyj
    0.38
    masing
    0.38
    分别
    0.38
    MaxScaler
    0.38
    ➌
    0.37
    それぞれの
    0.37
    POSITIVE LOGITS
     toe
    0.38
     toes
    0.38
     pulse
    0.37
     atenção
    0.37
     Restricted
    0.36
     certific
    0.36
     HTTP
    0.36
    omol
    0.36
    self
    0.36
     another
    0.36
    Activations Density 0.019%

    No Known Activations