© 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. 10735
    Prev
    Next
    INDEX
    Explanations

    multilingual requests and instructions

    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
     ik
    1.82
     oike
    1.76
     ich
    1.72
     '%'
    1.69
    ATTER
    1.68
    そこで
    1.63
     метою
    1.63
     dirname
    1.61
     ikan
    1.61
     आरोपों
    1.61
    POSITIVE LOGITS
    نه
    1.71
    વ
    1.57
    পর
    1.57
    ral
    1.52
    ய
    1.50
     Prel
    1.49
    не
    1.49
    বি
    1.48
    st
    1.46
     Measure
    1.44
    Activations Density 0.000%

    No Known Activations