© 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. 108655
    Prev
    Next
    INDEX
    Explanations

    queue articles

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

    Pipeline Architecture, precise timing, Nail Art Set

    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
     malef
    0.48
     аппара
    0.44
     ми
    0.44
     ke
    0.42
     столь
    0.41
     미
    0.41
     transcendental
    0.41
     пациента
    0.41
    変
    0.41
    ್ರ
    0.40
    POSITIVE LOGITS
    হাট
    0.51
    നും
    0.50
    bians
    0.49
    നി
    0.49
    plin
    0.48
    良好的
    0.48
    ystyle
    0.47
    ج
    0.47
    وبر
    0.46
    দায়
    0.46
    Activations Density 0.002%

    No Known Activations