© 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. 168723
    Prev
    Next
    INDEX
    Explanations

    name and address

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

    quantities and foreign words

    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
    Clinical
    0.46
    Supporting
    0.45
     main
    0.43
    Pharmac
    0.43
     □
    0.43
    はある
    0.42
     المق
    0.41
    >/
    0.40
     clinical
    0.40
    ння
    0.40
    POSITIVE LOGITS
    adır
    0.51
     inflación
    0.50
    ເລັກ
    0.48
    larını
    0.48
    ＿
    0.47
     Mn
    0.46
    лия
    0.45
    rö
    0.44
     İran
    0.44
     deduct
    0.43
    Activations Density 0.001%

    No Known Activations