© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122682
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations with negative numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
    省
    0.43
     reaction
    0.39
    reaction
    0.38
    ه‌ی
    0.37
    ляются
    0.36
    enzyme
    0.35
    scss
    0.35
    ibs
    0.35
     省
    0.35
     વખ
    0.34
    POSITIVE LOGITS
     (-
    0.50
    +(-
    0.49
     Minus
    0.47
     माइनस
    0.45
     subtract
    0.45
    subtract
    0.45
     subtracting
    0.45
     $(-
    0.44
    (-
    0.43
    {(-
    0.43
    Activations Density 0.003%

    No Known Activations