© 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. 52717
    Prev
    Next
    INDEX
    Explanations

    Presidential adviser, their instructions

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

    related administrative or structural terms

    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
    estimators
    0.48
    뺄
    0.48
    лм
    0.46
    큼
    0.46
     golfers
    0.45
     égales
    0.45
    бак
    0.45
    ч
    0.45
    솝
    0.45
    ेशनल
    0.44
    POSITIVE LOGITS
     επίσης
    0.54
     criteria
    0.50
     également
    0.49
     characteristics
    0.48
     मुख्यतः
    0.48
     Criteria
    0.47
     ide
    0.47
     identific
    0.47
     inoltre
    0.46
     priority
    0.46
    Activations Density 0.000%

    No Known Activations