© 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. 249812
    Prev
    Next
    INDEX
    Explanations

    specific categories or items

    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
    곶
    0.51
    ان
    0.50
    ین
    0.49
    覚えて
    0.48
    ノル
    0.47
    Elementos
    0.46
    లో
    0.45
    롯데
    0.45
    在庫
    0.44
    وك
    0.44
    POSITIVE LOGITS
    ups
    0.56
     Mohan
    0.48
    force
    0.47
    women
    0.45
     แ
    0.45
    wards
    0.45
    anc
    0.44
     পরিচ
    0.44
    success
    0.44
    lll
    0.44
    Activations Density 0.001%

    No Known Activations