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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69302
    Prev
    Next
    INDEX
    Explanations

    Ross Geller, Rottweiler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    oglobin
    2.01
    退休
    1.80
    ️
    1.80
    retired
    1.77
    ży
    1.72
    mandu
    1.71
    leveland
    1.71
    cluding
    1.71
     favorito
    1.69
    ektion
    1.69
    POSITIVE LOGITS
    syscall
    1.46
    ouw
    1.46
     ويع
    1.41
    PERTIES
    1.34
    チョコ
    1.32
    述
    1.32
    ::<
    1.29
     aspecto
    1.29
     גם
    1.29
     cuadrada
    1.28
    Activations Density 0.001%

    No Known Activations