© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1666
    Prev
    Next
    INDEX
    Explanations

    Differences in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     Dentro
    0.81
     внутри
    0.78
    Dentro
    0.74
    áról
    0.74
    臤
    0.74
    ésére
    0.73
    ებზე
    0.72
     Beneath
    0.72
     пределах
    0.72
     atop
    0.72
    POSITIVE LOGITS
     in
    2.91
     dalam
    2.28
     في
    2.12
     в
    2.08
    ใน
    2.03
     în
    1.99
    In
    1.94
     In
    1.87
     trong
    1.75
     ใน
    1.73
    Activations Density 1.461%

    No Known Activations