© 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. 187862
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and collocations

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

    stack overflow issues

    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
    アメリカ
    0.48
    UK
    0.47
     Анг
    0.44
     England
    0.42
     Calculator
    0.41
    撥
    0.41
     ОС
    0.41
     Equation
    0.40
     ува
    0.40
    UI
    0.40
    POSITIVE LOGITS
    创作
    0.54
     sporad
    0.54
    ⵢ
    0.52
    idlertid
    0.51
     ساخت
    0.50
    ‌شده
    0.50
     forgo
    0.48
    㕣
    0.48
     مراسم
    0.47
     หาก
    0.47
    Activations Density 0.001%

    No Known Activations