© 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. 131537
    Prev
    Next
    INDEX
    Explanations

    local schools, each animal, everyday language

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

    faster growth

    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
    міністра
    0.48
     cross
    0.46
    npc
    0.45
    anskrit
    0.43
    🕋
    0.43
     Magde
    0.42
     privato
    0.42
     foreigner
    0.41
    跨
    0.41
     NPC
    0.41
    POSITIVE LOGITS
    HttpHeaders
    0.50
     मू
    0.46
    ारों
    0.45
     inac
    0.45
    backs
    0.43
     olması
    0.42
     तुर
    0.42
     infallible
    0.42
    滢
    0.42
     yanı
    0.42
    Activations Density 0.000%

    No Known Activations