© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1797
    Prev
    Next
    INDEX
    Explanations

    math notation or 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
     onboarding
    0.49
     customtkinter
    0.42
    枥
    0.42
     શુભેચ્છ
    0.42
    📮
    0.42
    частли
    0.41
     Stewardship
    0.40
    营销
    0.40
    దన
    0.40
    ꒷
    0.39
    POSITIVE LOGITS
    sqrt
    0.54
     sqrt
    0.52
    mathcal
    0.52
     epsilon
    0.48
    epsilon
    0.47
    usepackage
    0.47
     ε
    0.46
     σ
    0.45
     displaystyle
    0.45
    ln
    0.44
    Activations Density 0.002%

    No Known Activations