© 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. 222394
    Prev
    Next
    INDEX
    Explanations

    coordinating events, important details, walkway bridge

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

    pressure drop

    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
    وفة
    0.52
    مجھے
    0.49
    петров
    0.47
    职务
    0.47
    WithOwner
    0.46
    高考
    0.46
    Poppins
    0.46
    祐
    0.46
    警方
    0.45
    绩效
    0.45
    POSITIVE LOGITS
     (
    0.64
     BA
    0.56
     neigh
    0.54
     sho
    0.54
     lesson
    0.54
     researchers
    0.52
     stud
    0.52
     decl
    0.52
     BF
    0.52
    ),
    0.50
    Activations Density 0.001%

    No Known Activations