© 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. 142117
    Prev
    Next
    INDEX
    Explanations

    ordinal dates

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

    rather than or where

    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
    if
    0.59
     最
    0.55
    ®
    0.54
     Niagara
    0.50
    °
    0.49
    Î
    0.48
    ¢
    0.48
     সর্বাধিক
    0.47
    -
    0.46
    ain
    0.46
    POSITIVE LOGITS
     Meinung
    0.53
    뺨
    0.48
     hilfreich
    0.48
    ساعدة
    0.48
     nötig
    0.47
     hilfre
    0.47
     Jalis
    0.46
     Ezek
    0.46
     Teilen
    0.45
    وجه
    0.44
    Activations Density 0.001%

    No Known Activations