© 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. 73335
    Prev
    Next
    INDEX
    Explanations

    quad + specific noun

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

    demand for exploitation

    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
    ны
    0.54
     nhất
    0.53
    гід
    0.53
    но
    0.52
    니
    0.50
    اء
    0.50
    д
    0.47
    د
    0.47
    ppsala
    0.45
    дился
    0.45
    POSITIVE LOGITS
     doma
    0.48
     products
    0.48
     produkty
    0.47
     materials
    0.47
     materiales
    0.47
     presentes
    0.47
     Requests
    0.46
     produkter
    0.46
     Ş
    0.46
     problemas
    0.46
    Activations Density 0.002%

    No Known Activations