© 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. 95482
    Prev
    Next
    INDEX
    Explanations

    characteristics, segmenting or grouping

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

    AI advice, product manager, fossil record

    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
    其他
    0.47
    وده
    0.43
    lecting
    0.43
    )_{\
    0.41
     বিবিসি
    0.41
    且
    0.41
    }_{\
    0.40
     spree
    0.40
     зді
    0.39
     weekend
    0.39
    POSITIVE LOGITS
    j
    0.59
     एज
    0.54
    vär
    0.53
     ग्रेट
    0.52
    iz
    0.50
     List
    0.50
     Algonquin
    0.50
    ड
    0.49
    v
    0.49
    roep
    0.48
    Activations Density 0.000%

    No Known Activations