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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106800
    Prev
    Next
    INDEX
    Explanations

    product descriptions with "About"

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

    martial arts, warnings against

    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
     chauffeur
    0.46
    ه
    0.44
     흔
    0.44
    ↵↵
    0.43
    diendo
    0.43
     focussing
    0.43
     воздей
    0.42
    祟
    0.41
     посто
    0.41
     шаблон
    0.41
    POSITIVE LOGITS
     attravers
    0.57
     associ
    0.50
     intenz
    0.48
    িয়ার
    0.48
     adquir
    0.48
    arms
    0.48
     पाँच
    0.47
    ระหว่าง
    0.47
     অভিম
    0.47
     adquirido
    0.46
    Activations Density 0.000%

    No Known Activations