© 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. 6683
    Prev
    Next
    INDEX
    Explanations

    amount, total, salary, revenue, count, value

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

    calculating sums counts totals

    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
     ermög
    0.55
    诗人
    0.52
     झरने
    0.52
     ప్రాంత
    0.52
    স্থানে
    0.52
    佛教
    0.52
    郯
    0.52
    神经
    0.51
     مسجد
    0.51
     দার্শনিক
    0.50
    POSITIVE LOGITS
     total
    1.03
     calculation
    1.03
     totals
    1.02
     calculated
    1.02
    total
    1.00
     calculate
    1.00
     calculates
    1.00
     calculations
    0.99
    calculate
    0.99
     amount
    0.97
    Activations Density 0.034%

    No Known Activations