© 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. 236794
    Prev
    Next
    INDEX
    Explanations

    legal countrymen

    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
    摟
    0.48
    জিৎ
    0.46
     سٹ
    0.46
     прогре
    0.46
     якщо
    0.45
     ہوجائے
    0.45
    ці
    0.45
     империи
    0.45
     rozwoju
    0.44
    櫥
    0.44
    POSITIVE LOGITS
    A
    0.53
    a
    0.46
     regs
    0.44
     P
    0.43
    auml
    0.43
     لائ
    0.43
    k
    0.43
     லை
    0.43
     Ley
    0.42
    电动
    0.41
    Activations Density 0.000%

    No Known Activations