© 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. 198701
    Prev
    Next
    INDEX
    Explanations

    new album or version

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

    but doesn't guarantee

    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
     emissions
    0.49
     abatement
    0.48
     육
    0.47
     போரா
    0.46
     rejection
    0.46
    следование
    0.45
    kati
    0.45
     કરવાની
    0.43
     assessment
    0.42
     Emissions
    0.42
    POSITIVE LOGITS
    Ա
    0.50
    小于
    0.49
     irmão
    0.49
    现在
    0.49
    おり
    0.47
    シングル
    0.47
    瑞
    0.47
     complicate
    0.47
    大街
    0.46
    大
    0.46
    Activations Density 0.001%

    No Known Activations