© 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. 233728
    Prev
    Next
    INDEX
    Explanations

    installation, trip, course, make

    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
     potenz
    0.50
     медицин
    0.47
    Occupation
    0.47
     стри
    0.46
     },{
    0.46
    varez
    0.45
     conformément
    0.45
     liés
    0.44
     приготов
    0.44
    Dé
    0.44
    POSITIVE LOGITS
    會
    0.48
     time
    0.46
    time
    0.45
    重建
    0.44
     League
    0.44
    会
    0.44
    !'
    0.44
    !।
    0.43
     London
    0.43
     Greek
    0.42
    Activations Density 0.001%

    No Known Activations