© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167638
    Prev
    Next
    INDEX
    Explanations

    multiplication and numerical listing

    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_40_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
    譞
    0.39
    常常
    0.38
    infoHeader
    0.37
     Simultaneous
    0.37
    选题
    0.35
     Different
    0.35
    不同
    0.34
     simultaneous
    0.34
    તુ
    0.34
    Different
    0.34
    POSITIVE LOGITS
     multiplied
    1.27
     twice
    1.20
     ×
    1.18
     multiplicado
    1.13
    ×
    1.13
    twice
    1.06
     zweimal
    1.03
     multiply
    1.01
    multiply
    0.97
     Multiply
    0.96
    Activations Density 0.063%

    No Known Activations