© 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. 219627
    Prev
    Next
    INDEX
    Explanations

    multiplication expressions

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

    mathematical multiplication

    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
     подчи
    0.45
     Differentiation
    0.45
     сумма
    0.42
    顼
    0.42
     fifo
    0.40
     тренер
    0.39
     плюс
    0.39
     subordination
    0.39
     differentiation
    0.38
     Cooks
    0.38
    POSITIVE LOGITS
    multiply
    0.60
    Multiply
    0.57
    乘
    0.51
     Multiply
    0.50
     곱
    0.50
    ∏
    0.47
     multiplying
    0.46
     multiplies
    0.45
    productId
    0.45
    prod
    0.44
    Activations Density 0.007%

    No Known Activations