© 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. 199216
    Prev
    Next
    INDEX
    Explanations

    joint accounts and collections

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

    programming related words

    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
    ペーン
    0.48
    נים
    0.47
     palate
    0.47
    Chlor
    0.47
    ام
    0.47
    รส
    0.45
    Restaurant
    0.45
     quartzite
    0.45
     runga
    0.45
    آ
    0.45
    POSITIVE LOGITS
    s
    0.56
     ตัว
    0.54
    ipt
    0.53
     来自
    0.53
     আইন
    0.50
    def
    0.49
    正确
    0.49
     Almighty
    0.49
     দেয়া
    0.49
     วิชา
    0.49
    Activations Density 0.000%

    No Known Activations