© 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. 69578
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    service off, lab online, protection

    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
     celu
    0.49
    anil
    0.48
     desejo
    0.48
    Ivan
    0.48
    名为
    0.47
    ای
    0.46
    ан
    0.46
    "],"
    0.46
    ENA
    0.45
     Bars
    0.45
    POSITIVE LOGITS
    င်း
    0.46
    יים
    0.45
     처리
    0.45
    ۰۰
    0.45
    處理
    0.45
    verz
    0.44
    ᄂ
    0.43
     měli
    0.43
    uegos
    0.42
    會有
    0.42
    Activations Density 0.000%

    No Known Activations