© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57176
    Prev
    Next
    INDEX
    Explanations

    whether a condition is met

    np_acts-logits-general · gemini-2.5-flash-lite

    if/whether checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ধর
    0.43
    anediyl
    0.39
    咡
    0.39
    niejszych
    0.38
    䨋
    0.38
    หย
    0.37
    เริ่มต้น
    0.37
     пише
    0.36
    outgoing
    0.36
    長
    0.35
    POSITIVE LOGITS
     apakah
    0.62
     whether
    0.60
    是否
    0.60
    かどうか
    0.59
     是否
    0.57
    判定
    0.55
    能否
    0.55
     Whether
    0.54
    IsValid
    0.54
     isValid
    0.54
    Activations Density 0.005%

    No Known Activations