© 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. 102799
    Prev
    Next
    INDEX
    Explanations

    Long words and names

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

    value, cost, undertaking, and difficulty

    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
     திமுக
    0.54
     लंबित
    0.52
     판
    0.50
     साबित
    0.48
     डिफर
    0.48
     रेट
    0.48
     दक्षिण
    0.47
     कार्यकारी
    0.47
     grievous
    0.47
     सत्यापित
    0.47
    POSITIVE LOGITS
    ין
    0.53
    {
    0.49
    ه
    0.48
    ายน
    0.47
     Jonny
    0.47
    jazd
    0.45
    מ
    0.45
    ين
    0.45
    חיל
    0.45
    ট
    0.44
    Activations Density 0.001%

    No Known Activations