© 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. 41-GEMMASCOPE-2-RES-262K
    7. 57354
    Prev
    Next
    INDEX
    Explanations

    piecewise functions or switches

    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_all/layer_41_width_262k_l0_big
    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
    颔
    0.47
     humanities
    0.40
    ovariant
    0.40
     اہ
    0.39
    աշ
    0.38
    TimeString
    0.38
    缦
    0.38
    䛊
    0.38
     successive
    0.38
     сфе
    0.38
    POSITIVE LOGITS
     piecewise
    0.69
    switch
    0.65
     switch
    0.63
     switched
    0.62
     switches
    0.59
     स्विच
    0.59
     switching
    0.59
     Switching
    0.58
    Switch
    0.56
    スイッチ
    0.56
    Activations Density 0.002%

    No Known Activations