© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 67
    Prev
    Next
    INDEX
    Explanations

    intensifiers or qualifiers

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

    potentially avoid

    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_16k_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
     һәм
    0.19
     তাছাড়া
    0.17
     և
    0.17
     صہی
    0.17
     ಹಾಗೂ
    0.17
     மற்றும்
    0.16
     แต่
    0.16
    และการ
    0.16
     isotherms
    0.16
    および
    0.16
    POSITIVE LOGITS
     have
    0.19
     være
    0.18
    have
    0.18
    y
    0.18
    neho
    0.17
     trochu
    0.17
    erweise
    0.17
    csak
    0.17
    成为
    0.17
     csak
    0.16
    Activations Density 3.109%

    No Known Activations