© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    like / wildcard pattern matching

    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
     değişiklik
    1.97
     Juego
    1.90
     تهیه
    1.81
     dàn
    1.81
     neuesten
    1.75
    MouseDown
    1.72
     야
    1.72
    Minimize
    1.72
     çiz
    1.71
    MouseMove
    1.69
    POSITIVE LOGITS
    ifient
    1.81
    i
    1.74
    pati
    1.68
    trunk
    1.67
    {|
    1.67
    gine
    1.67
    bit
    1.65
    т
    1.64
    uct
    1.63
    atron
    1.62
    Activations Density 0.001%

    No Known Activations