© 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. 180476
    Prev
    Next
    INDEX
    Explanations

    accommodation, instrumentation, apprentice, officers, nonstick

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

    Node.js express app programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ୨
    0.49
     dropping
    0.49
     injuring
    0.49
     infractions
    0.47
     interceptions
    0.46
     compartments
    0.46
     injecting
    0.46
     lỗ
    0.46
     khối
    0.46
    ง
    0.45
    POSITIVE LOGITS
    gara
    0.52
    zeugt
    0.52
    persona
    0.48
    ag
    0.47
    esen
    0.47
    apat
    0.45
    layered
    0.45
    ̒
    0.44
    chef
    0.44
    ্ম্ম
    0.44
    Activations Density 0.000%

    No Known Activations