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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 8196
    Prev
    Next
    INDEX
    Explanations

    nationalities and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    其他
    0.99
    يا
    0.92
    Một
    0.80
    り
    0.79
    Με
    0.78
    teki
    0.78
     igra
    0.76
     isang
    0.76
     innych
    0.75
    OfInterest
    0.75
    POSITIVE LOGITS
     an
    1.03
    ore
    0.85
    ETT
    0.84
    ни
    0.81
    ET
    0.77
     on
    0.77
    elling
    0.76
    ä
    0.73
    களில்
    0.71
    CH
    0.71
    Activations Density 0.082%

    No Known Activations