© 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. 241585
    Prev
    Next
    INDEX
    Explanations

    up the ante

    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
     السادس
    0.48
    ඩ්
    0.48
     초
    0.48
     करण
    0.48
     ২৭
    0.47
    बुक
    0.47
     কোল
    0.46
     करिकुलम
    0.46
     स्प
    0.45
     التن
    0.45
    POSITIVE LOGITS
     delay
    0.49
    0
    0.49
    もあり
    0.48
    Добрый
    0.48
     caffè
    0.46
     indulgence
    0.46
     whimsical
    0.45
    一方で
    0.44
     idle
    0.43
    ُمْ
    0.43
    Activations Density 0.000%

    No Known Activations