© 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. 166813
    Prev
    Next
    INDEX
    Explanations

    worked perfectly

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

    if it's

    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
    ១
    0.52
    ometimes
    0.50
     Право
    0.49
     सेवक
    0.48
    ㅋㅋ
    0.47
    躊
    0.46
    ۱۳
    0.46
     گے
    0.46
    वात
    0.46
    workouts
    0.46
    POSITIVE LOGITS
     infused
    0.52
     deployed
    0.49
     unleashed
    0.49
     hydrolyzed
    0.49
     on
    0.47
     collaborated
    0.46
     ethylene
    0.46
     pounds
    0.45
     ionic
    0.45
    ↵
    0.45
    Activations Density 0.001%

    No Known Activations