© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 248594
    Prev
    Next
    INDEX
    Explanations

    grants for, initially struck, rates scaling

    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
    越大
    0.47
     concentración
    0.45
    ंक
    0.44
    лянчук
    0.44
    璺
    0.44
    اة
    0.44
     بو
    0.42
    特
    0.42
    멱
    0.42
     cámaras
    0.42
    POSITIVE LOGITS
     variegated
    0.54
     Dlatego
    0.52
     luckily
    0.52
     fortunately
    0.50
     because
    0.50
     সেপ্ট
    0.47
     Alloy
    0.47
     Luckily
    0.47
     Aufgrund
    0.47
     ধন্যবাদ
    0.47
    Activations Density 0.000%

    No Known Activations