© 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. 187154
    Prev
    Next
    INDEX
    Explanations

    a ... rates

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

    ready to perform actions

    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
    orphic
    0.54
    تو
    0.52
    ت
    0.51
    تش
    0.45
    懲
    0.44
    دن
    0.44
    conducting
    0.44
    لز
    0.43
    頜
    0.43
    ื
    0.43
    POSITIVE LOGITS
     deux
    0.55
     ១
    0.52
     двумя
    0.52
     komentar
    0.50
     dimulai
    0.48
     hacemos
    0.48
     Menteri
    0.47
     provoqu
    0.47
     heroine
    0.47
     Kuala
    0.46
    Activations Density 0.000%

    No Known Activations