© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9831
    Prev
    Next
    INDEX
    Explanations

    class constructors or initialization

    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_13_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
     ا
    1.36
     الم
    1.22
    ­
    1.18
     س
    1.18
     مع
    1.16
    ّ
    1.13
     ب
    1.13
     ン
    1.12
    Cl
    1.11
     ر
    1.11
    POSITIVE LOGITS
     vattum
    1.37
     stockbild
    1.29
    ecommerce
    1.24
    studentid
    1.22
    parametri
    1.20
    openid
    1.19
    lanelet
    1.19
    tuple
    1.18
     hyperbol
    1.18
    weapp
    1.17
    Activations Density 0.025%

    No Known Activations