© 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. 108628
    Prev
    Next
    INDEX
    Explanations

    killed by

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

    lessons, MIN, geopathic, soldiers, shapes, mustangs, telephone

    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
    ي
    0.50
     contento
    0.48
    ционер
    0.47
    す
    0.46
    具体的
    0.43
    ضا
    0.43
    重点
    0.43
    ла
    0.42
     Möglich
    0.41
    ndarray
    0.41
    POSITIVE LOGITS
    brake
    0.51
     Prony
    0.45
     शत्र
    0.44
    टा
    0.44
     bordo
    0.43
     BATH
    0.43
    
    0.43
    nltk
    0.42
    ASTM
    0.42
    নিং
    0.42
    Activations Density 0.001%

    No Known Activations