© 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. 227133
    Prev
    Next
    INDEX
    Explanations

    locations, events, descriptions

    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
     shabby
    0.61
     напряжения
    0.57
    RequestListener
    0.53
    CORPOR
    0.52
    sqcup
    0.51
    टेस्ट
    0.49
     фара
    0.48
    哴
    0.48
    SetUp
    0.47
    ToString
    0.47
    POSITIVE LOGITS
    在
    0.54
     Items
    0.45
    yip
    0.45
    פות
    0.45
    aro
    0.43
     ipc
    0.42
     idioms
    0.42
     in
    0.42
    送料
    0.42
     Incre
    0.41
    Activations Density 0.000%

    No Known Activations