© 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. 135540
    Prev
    Next
    INDEX
    Explanations

    types of devices

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

    laws, formats, As, topics, Change, question, Acela

    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
    鎊
    0.48
     који
    0.48
    adayo
    0.47
    ീകരണ
    0.46
     dormitorios
    0.46
     питань
    0.45
    唥
    0.45
     кількість
    0.45
     дос
    0.45
     સંખ્યા
    0.45
    POSITIVE LOGITS
    جو
    0.57
    U
    0.53
    ون
    0.52
    O
    0.50
    У
    0.49
     Society
    0.49
    ""
    0.49
    ס
    0.48
    ع
    0.48
     Smooth
    0.48
    Activations Density 0.000%

    No Known Activations