© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    C++ multithreading

    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
    er
    1.63
    enburg
    1.46
    hul
    1.45
    irikan
    1.40
    ための
    1.39
    erci
    1.28
    고
    1.26
    ele
    1.25
    gur
    1.23
    というのが
    1.23
    POSITIVE LOGITS
    섦
    1.48
    了我
    1.45
     ा
    1.44
     Subscriber
    1.43
     GestureDetector
    1.42
    addField
    1.41
    ‌ನ
    1.41
    Commande
    1.41
     коль
    1.40
    デア
    1.40
    Activations Density 0.183%

    No Known Activations