© 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. 117624
    Prev
    Next
    INDEX
    Explanations

    while loops

    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
    ermos
    0.50
    類型
    0.48
    強調
    0.46
    idão
    0.44
    ider
    0.42
     강조
    0.41
    證
    0.41
    iophor
    0.40
     얘가
    0.40
     메서
    0.40
    POSITIVE LOGITS
    ছোট
    0.48
     otur
    0.47
    Voids
    0.47
    س
    0.47
     niedr
    0.46
    YD
    0.45
     chern
    0.45
     ponctu
    0.44
    ELD
    0.44
     doy
    0.44
    Activations Density 0.000%

    No Known Activations