© 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. 35600
    Prev
    Next
    INDEX
    Explanations

    searching for design

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

    sections 721 and 351

    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
    </strong>
    0.55
    ↵
    0.53
     និង
    0.51
    Swan
    0.51
    Dev
    0.49
    ني
    0.48
    Design
    0.48
     Вер
    0.48
    Link
    0.47
    </h4>
    0.47
    POSITIVE LOGITS
     subpar
    0.47
     renfer
    0.47
     mozzarella
    0.45
     disenfranch
    0.45
     oval
    0.44
     suboptimal
    0.44
     chiese
    0.44
     valence
    0.43
     comentó
    0.43
     cuyos
    0.43
    Activations Density 0.001%

    No Known Activations