© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 10944
    Prev
    Next
    INDEX
    Explanations

    vba variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    өн
    3.04
    uhnya
    2.87
     оригіналу
    2.73
    ษ
    2.62
    umlahan
    2.59
    urence
    2.52
    WhiteElo
    2.46
     pomocą
    2.43
    idded
    2.42
    ۥ
    2.38
    POSITIVE LOGITS
    ే
    3.93
    ا
    3.71
    നി
    2.81
    o
    2.78
    tension
    2.68
    𝒐
    2.64
    ming
    2.60
    دق
    2.56
     Marquis
    2.55
    বাত
    2.54
    Activations Density 0.002%

    No Known Activations