© 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. 87028
    Prev
    Next
    INDEX
    Explanations

    clinical topics

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

    exploit them

    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
    漣
    0.53
     Puebla
    0.49
     बुन्देल
    0.47
     Tapat
    0.47
     Verbrauch
    0.46
     Saginaw
    0.45
    闓
    0.45
     Juego
    0.44
     Sicher
    0.44
    vidas
    0.44
    POSITIVE LOGITS
    同一
    0.41
     نظامی
    0.41
     ஒன்றை
    0.40
    гий
    0.40
    0.38
     monoxide
    0.38
    務
    0.38
    奢
    0.38
    لز
    0.38
    recycl
    0.37
    Activations Density 0.000%

    No Known Activations