© 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. 162118
    Prev
    Next
    INDEX
    Explanations

    percent of

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

    assign each

    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
     tournée
    0.50
    ここは
    0.48
    コンサート
    0.48
    ق
    0.47
    Tha
    0.46
    サービスの
    0.46
    Pré
    0.46
    した
    0.45
    popupIsOpen
    0.45
    تع
    0.44
    POSITIVE LOGITS
     grilling
    0.57
     krom
    0.53
     potting
    0.53
     at
    0.47
     ครั้ง
    0.46
     gluing
    0.46
     dequeue
    0.46
     약
    0.46
     bind
    0.46
     ting
    0.45
    Activations Density 0.000%

    No Known Activations