© 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. 251149
    Prev
    Next
    INDEX
    Explanations

    sales and securities

    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
    :
    0.54
    1
    0.53
     two
    0.50
    ad
    0.48
    st
    0.48
     produit
    0.47
     best
    0.47
     three
    0.47
     pedigree
    0.46
     sake
    0.46
    POSITIVE LOGITS
    codetest
    0.51
    ótico
    0.47
    簹
    0.46
    вича
    0.46
     Dislocations
    0.46
    薁
    0.46
    経済
    0.45
     পারেনা
    0.44
    úscula
    0.44
     انگل
    0.44
    Activations Density 0.001%

    No Known Activations