© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30697
    Prev
    Next
    INDEX
    Explanations

    speedy companion

    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_all/layer_41_width_262k_l0_big
    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
     publicaciones
    0.39
    {[\
    0.37
     Архивная
    0.37
    ჷ
    0.37
     চলেছে
    0.36
    蠣
    0.36
    Iowa
    0.35
    居民
    0.35
    ㆍ
    0.35
    Im
    0.34
    POSITIVE LOGITS
     Speedy
    0.43
     speed
    0.42
     Speed
    0.41
     scholar
    0.40
     Gentleman
    0.38
     speedy
    0.38
     سرعت
    0.38
     accelerated
    0.37
    speed
    0.37
     !!!
    0.36
    Activations Density 0.000%

    No Known Activations