© 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. 239081
    Prev
    Next
    INDEX
    Explanations

    supporting couponwitme.com

    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
    Renderer
    0.44
     Brochure
    0.44
    ↵
    0.42
     SRP
    0.42
     Vou
    0.42
     Featuring
    0.42
     WAS
    0.41
     Plush
    0.41
     Wrapper
    0.41
    successor
    0.41
    POSITIVE LOGITS
    си
    0.51
    ී
    0.50
    ॉर्ट
    0.50
    ého
    0.49
    пси
    0.49
    жига
    0.46
    स्ट्रेशन
    0.46
    ज़ी
    0.46
    делать
    0.46
    сист
    0.45
    Activations Density 0.002%

    No Known Activations