© 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. 186929
    Prev
    Next
    INDEX
    Explanations

    skills and services

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

    dangers of extremism

    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
     Conoc
    0.54
     ليست
    0.53
     بينما
    0.53
     সহায়তা
    0.52
     compreensão
    0.52
     enfrenta
    0.51
     nommé
    0.49
     还
    0.49
     వైర
    0.49
     pomoć
    0.49
    POSITIVE LOGITS
     ICI
    0.47
    ができる
    0.45
     photons
    0.44
     regimes
    0.44
     발생하는
    0.43
     unpredict
    0.43
     HCl
    0.42
    க்கெ
    0.42
    ICI
    0.42
     clf
    0.42
    Activations Density 0.000%

    No Known Activations