© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84784
    Prev
    Next
    INDEX
    Explanations

    logical and mathematical symbols

    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
     articulating
    0.43
     სისტ
    0.42
     стой
    0.42
    uiDesigner
    0.42
     articulation
    0.41
    組
    0.41
     quedar
    0.40
     литера
    0.39
     intArray
    0.39
     галу
    0.39
    POSITIVE LOGITS
    vdash
    0.49
     rhino
    0.41
    关系
    0.40
     Proper
    0.38
     ら
    0.37
     इं
    0.37
     mampu
    0.36
     दहा
    0.36
    Xiv
    0.36
    征
    0.35
    Activations Density 0.015%

    No Known Activations