© 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. 11672
    Prev
    Next
    INDEX
    Explanations

    conditional logic and code structure

    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
    𝖺
    0.46
    א
    0.37
     மலச்சிக்க
    0.37
    薔
    0.36
    齒
    0.35
     боле
    0.35
     comer
    0.34
    르
    0.34
     రె
    0.34
     식
    0.33
    POSITIVE LOGITS
    if
    0.46
    while
    0.38
    wijl
    0.37
    জিত
    0.35
    শ্চর্য
    0.35
    आईटी
    0.34
    াকুর
    0.34
    ্বেও
    0.34
    īgi
    0.33
    owały
    0.33
    Activations Density 0.000%

    No Known Activations