© 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. 108872
    Prev
    Next
    INDEX
    Explanations

    wedges in, it is

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

    stages, past, immediate, advanced

    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
    ك
    0.61
    6
    0.53
    A
    0.52
    B
    0.52
    :
    0.52
    T
    0.51
    о
    0.50
    OR
    0.50
    Q
    0.48
    Man
    0.47
    POSITIVE LOGITS
    ésil
    0.60
     délégation
    0.57
     prawidł
    0.54
     planète
    0.54
     scorpion
    0.53
     personne
    0.52
    ண்ணாம
    0.52
     tortue
    0.52
     மற்ற
    0.51
     paiement
    0.51
    Activations Density 0.001%

    No Known Activations