© 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. 22927
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and equations

    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
     संभा
    0.41
    लिसा
    0.37
     zah
    0.37
     নই
    0.36
    охра
    0.36
    洁
    0.36
     劉
    0.35
    Oliver
    0.34
     রাকাত
    0.34
    wiata
    0.34
    POSITIVE LOGITS
     curv
    0.40
    arctan
    0.39
    etan
    0.37
     obsolete
    0.37
     tanh
    0.37
     unsafe
    0.37
    tanh
    0.35
    "].
    0.35
     obso
    0.35
    atan
    0.34
    Activations Density 0.020%

    No Known Activations