© 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. 50980
    Prev
    Next
    INDEX
    Explanations

    currency or percentage changes

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

    writing styles and materials

    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
     irrespective
    0.47
     punctual
    0.47
     bipartite
    0.45
    ாண
    0.44
     invariable
    0.43
    ા
    0.43
    зни
    0.42
    ी
    0.42
     pří
    0.40
     disappro
    0.40
    POSITIVE LOGITS
     Labrador
    0.49
     snowboard
    0.49
     NASDAQ
    0.48
     Nike
    0.47
     الأخرى
    0.46
     labrador
    0.46
     nvidia
    0.45
     Samsung
    0.45
     лабора
    0.45
     거고
    0.44
    Activations Density 0.000%

    No Known Activations