© 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. 235521
    Prev
    Next
    INDEX
    Explanations

    tickets, awards, organize, training, blending

    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
    DLC
    0.49
     pathetic
    0.47
     pitiful
    0.46
     sih
    0.46
    tede
    0.46
    arakatuh
    0.46
    則是
    0.45
    чках
    0.44
    iéndose
    0.44
    綎
    0.44
    POSITIVE LOGITS
     baş
    0.47
     kodu
    0.47
     homogenization
    0.46
     complain
    0.46
     kształ
    0.46
     forg
    0.46
     altura
    0.46
     för
    0.45
     böl
    0.44
     fonksiyon
    0.44
    Activations Density 0.000%

    No Known Activations