© 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. 66978
    Prev
    Next
    INDEX
    Explanations

    choosing Retro, Dug, given, Gang

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

    Structuring and financing

    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
     имуще
    0.54
     संपत्ति
    0.50
    癱
    0.48
     svojim
    0.48
    reportBody
    0.47
    liğini
    0.47
    myY
    0.47
    neath
    0.47
     තම
    0.46
    nič
    0.46
    POSITIVE LOGITS
     Recommended
    0.51
     Drinks
    0.50
    <0x0D>
    0.50
     File
    0.49
     Xác
    0.49
     drinks
    0.49
    3
    0.48
     HER
    0.48
    :
    0.48
     Confirmation
    0.48
    Activations Density 0.000%

    No Known Activations