© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4656
    Prev
    Next
    INDEX
    Explanations

    spending, costs, financing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gefühl
    0.36
     text
    0.34
     ব্যাখ্যা
    0.34
     concerned
    0.34
     identifying
    0.34
    text
    0.33
     worded
    0.33
    勰
    0.33
     sy
    0.33
     ident
    0.32
    POSITIVE LOGITS
     expenses
    0.73
    expenses
    0.64
     финанси
    0.64
     purchases
    0.63
     expenditures
    0.62
     purchase
    0.62
     spese
    0.62
     خرید
    0.61
     costs
    0.59
     pricey
    0.59
    Activations Density 0.166%

    No Known Activations