© 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. 241063
    Prev
    Next
    INDEX
    Explanations

    Twentieth Century, filmmakers, airlines, football

    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
    לות
    0.52
    憐
    0.50
    線上
    0.47
    排行
    0.47
    頁
    0.47
    лари
    0.47
    賺
    0.47
    手機
    0.47
    噵
    0.46
     trouver
    0.46
    POSITIVE LOGITS
    airlines
    0.54
    Seattle
    0.53
    Pr
    0.51
    Mumbai
    0.51
    Shanghai
    0.50
    Hong
    0.50
    United
    0.49
     filmmakers
    0.49
    Minneapolis
    0.49
    Che
    0.49
    Activations Density 0.000%

    No Known Activations