© 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. 140056
    Prev
    Next
    INDEX
    Explanations

    maternal smoking

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

    trust region, individual role, scheduling tool

    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
    دام
    0.47
     beweg
    0.46
    fixed
    0.45
    beweg
    0.44
     slutt
    0.44
     voraus
    0.44
     Indo
    0.43
    وتر
    0.43
     bahas
    0.43
    轸
    0.43
    POSITIVE LOGITS
    ຫຼາຍ
    0.52
    ations
    0.49
     መሰ
    0.49
     હત્યા
    0.47
    াজার
    0.43
     એપ
    0.43
     certify
    0.42
    ages
    0.42
    ար
    0.42
     supplements
    0.42
    Activations Density 0.001%

    No Known Activations