© 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. 75746
    Prev
    Next
    INDEX
    Explanations

    increase levels

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

    Option 2

    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
    Rusty
    0.49
    LAMP
    0.45
    器
    0.45
    Ross
    0.44
    ვილი
    0.44
    罗斯
    0.44
    乔
    0.43
    Ро
    0.42
    ристо
    0.42
    之人
    0.42
    POSITIVE LOGITS
     Leibn
    0.55
     KPIs
    0.49
     ovat
    0.48
    ്
    0.47
     الذين
    0.47
     Einige
    0.47
     Chromatography
    0.46
     Assertion
    0.46
     dersimizde
    0.46
     tzw
    0.46
    Activations Density 0.001%

    No Known Activations