© 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. 183293
    Prev
    Next
    INDEX
    Explanations

    in front of environments

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

    work anniversary

    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
     Residual
    0.47
    ighet
    0.46
    residual
    0.46
    ,
    0.46
    iex
    0.45
     Scout
    0.45
     residual
    0.44
     find
    0.44
    find
    0.44
     enhance
    0.44
    POSITIVE LOGITS
    GEBURTS
    0.51
    苧
    0.48
    咘
    0.48
    hluk
    0.48
    aguars
    0.46
     多い
    0.46
    螓
    0.45
    лля
    0.45
    hipi
    0.45
    htub
    0.44
    Activations Density 0.001%

    No Known Activations