© 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. 176528
    Prev
    Next
    INDEX
    Explanations

    occasion cards

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

    no answer

    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
    ла
    0.51
    숲
    0.49
    景
    0.47
    연
    0.47
    墻
    0.45
    諫
    0.44
    폭
    0.44
    <0x0D>
    0.44
    بود
    0.43
    내가
    0.43
    POSITIVE LOGITS
    ociaż
    0.51
     carry
    0.50
     attentively
    0.48
     herhangi
    0.46
    yai
    0.46
    ();
    0.45
    Ո
    0.45
     ana
    0.44
     asam
    0.44
    yat
    0.44
    Activations Density 0.000%

    No Known Activations