© 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. 192860
    Prev
    Next
    INDEX
    Explanations

    tagged with words

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

    Denver Exploration

    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
    StarGo
    0.50
     ผ่าน
    0.50
     এগুলো
    0.48
     preparazione
    0.48
    uju
    0.46
     избежать
    0.46
     цієї
    0.46
     genome
    0.46
    Ook
    0.45
    ());
    0.45
    POSITIVE LOGITS
     Inver
    0.52
    L
    0.50
     बढ़ाकर
    0.49
    emont
    0.48
     Toler
    0.48
     Rox
    0.47
     Labor
    0.47
     Rusty
    0.47
     opi
    0.46
    改
    0.46
    Activations Density 0.000%

    No Known Activations