© 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. 114373
    Prev
    Next
    INDEX
    Explanations

    foreign language introductions

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

    specifics and requirements

    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
    S
    0.46
     cartes
    0.42
    减
    0.41
     balancer
    0.39
     alen
    0.39
     vern
    0.39
    u
    0.39
    இந்நிலையில்
    0.38
    ت
    0.38
    صبح
    0.38
    POSITIVE LOGITS
     работников
    0.53
     выполнение
    0.50
     законом
    0.50
     изу
    0.48
    ÓN
    0.48
     текста
    0.47
     মায়ের
    0.47
     ખૂબ
    0.47
     Гла
    0.47
    ㌔
    0.47
    Activations Density 0.001%

    No Known Activations