© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23428
    Prev
    Next
    INDEX
    Explanations

    dictionary key access

    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
     pairing
    0.40
    ய
    0.40
     Assign
    0.40
    ペア
    0.40
    Season
    0.39
     assegn
    0.39
     сезон
    0.38
     artificially
    0.38
    ۵
    0.38
    मौसम
    0.38
    POSITIVE LOGITS
     keys
    0.45
    keys
    0.44
    keySet
    0.43
     interes
    0.41
    이어
    0.40
     interest
    0.39
     이어
    0.39
     Bored
    0.39
     iter
    0.38
     Keys
    0.38
    Activations Density 0.001%

    No Known Activations