© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12297
    Prev
    Next
    INDEX
    Explanations

    chemical reaction

    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
    iasa
    2.51
    꿋
    2.43
    oriale
    2.33
    vres
    2.29
    мино
    2.28
    ieniu
    2.28
    ﻥ
    2.24
    esar
    2.18
    ioen
    2.18
    emente
    2.18
    POSITIVE LOGITS
    ی
    2.77
    تف
    2.66
    ു
    2.62
    ال
    2.60
    म
    2.59
     ré
    2.55
    スコ
    2.50
    BUS
    2.49
    ing
    2.47
     ==========
    2.47
    Activations Density 0.008%

    No Known Activations