© 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. 16-GEMMASCOPE-2-RES-262K
    7. 16307
    Prev
    Next
    INDEX
    Explanations

    fees, duties, taxes, rates

    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_16_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
     a
    0.73
     with
    0.67
     weather
    0.67
     organizations
    0.67
     hydroxy
    0.66
     adalah
    0.65
     providing
    0.64
     sy
    0.63
     homeless
    0.63
     s
    0.62
    POSITIVE LOGITS
    يد
    0.76
    as
    0.75
     ترك
    0.71
    та
    0.66
     बीटल
    0.66
    taxes
    0.64
    Penalty
    0.62
    fees
    0.61
    to
    0.60
    ას
    0.60
    Activations Density 0.009%

    No Known Activations