© 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. 186106
    Prev
    Next
    INDEX
    Explanations

    production and construction

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

    skip offset

    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
     فیصلے
    0.50
     perjury
    0.48
    ನ್ನಡ
    0.47
     çar
    0.47
     sadece
    0.47
     terjadi
    0.46
     huwa
    0.46
    擘
    0.45
     lettera
    0.45
     neuritis
    0.45
    POSITIVE LOGITS
    Determin
    0.47
     идеально
    0.42
     allotted
    0.41
     Shandong
    0.40
    irá
    0.40
     ascertain
    0.40
     ঈশ্বর
    0.39
     spend
    0.39
     belt
    0.39
     Spend
    0.38
    Activations Density 0.002%

    No Known Activations