© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    code comments and functions

    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
    𝗜
    3.04
    Ȧ
    2.67
    निंग
    2.61
     toc
    2.55
    <unused1938>
    2.53
     betray
    2.51
    𝗢
    2.50
    त
    2.50
    乀
    2.48
    DECLARE
    2.48
    POSITIVE LOGITS
    western
    2.44
    agway
    2.33
     spoke
    2.30
    sten
    2.30
    үнд
    2.23
    gaon
    2.22
     விட்டு
    2.16
    ders
    2.16
    俭
    2.14
    өн
    2.12
    Activations Density 0.025%

    No Known Activations