© 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. 108107
    Prev
    Next
    INDEX
    Explanations

    continue to, evaluation of, without

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

    COBRA applies

    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
     voisins
    0.50
     Hoa
    0.49
     thóc
    0.48
     oats
    0.47
     ホ
    0.46
     Mạnh
    0.46
     buckwheat
    0.46
     spé
    0.45
     изделия
    0.44
    ()){
    0.44
    POSITIVE LOGITS
    am
    0.50
     chairperson
    0.46
    decoder
    0.46
    political
    0.46
    integration
    0.45
    EN
    0.45
    encoder
    0.44
    TE
    0.44
    PL
    0.44
    LEGO
    0.44
    Activations Density 0.000%

    No Known Activations