© 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. 145503
    Prev
    Next
    INDEX
    Explanations

    how long

    np_acts-logits-general · gemini-2.5-flash-lite

    founded in 2021

    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
     bì
    0.55
    觐
    0.53
     aDecoder
    0.52
     죄
    0.51
     currentDate
    0.50
     බ
    0.49
     مخطط
    0.48
     rétréci
    0.48
     utilisé
    0.47
     패
    0.46
    POSITIVE LOGITS
    .​
    0.48
     Fence
    0.47
    .&
    0.47
     alienated
    0.44
    links
    0.44
    inking
    0.44
    .}
    0.43
    гово
    0.43
    מ
    0.43
    k
    0.43
    Activations Density 0.001%

    No Known Activations