© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55628
    Prev
    Next
    INDEX
    Explanations

    asking 'what is' or 'how do'

    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_40_width_65k_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
    /
    0.53
     By
    0.48
     regardless
    0.46
     (
    0.45
     ("
    0.44
     :
    0.44
     ->
    0.43
    :
    0.43
     related
    0.43
     niemals
    0.43
    POSITIVE LOGITS
    究竟
    0.55
    actually
    0.54
     உண்மையில்
    0.54
     davvero
    0.53
     actually
    0.52
     elusive
    0.52
    到底
    0.51
    ogliamo
    0.50
     আসলে
    0.49
     एक्चुअली
    0.49
    Activations Density 0.076%

    No Known Activations