© 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. 11447
    Prev
    Next
    INDEX
    Explanations

    folder and directory structure

    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
     adverts
    1.46
     realised
    1.44
    £
    1.43
     ل
    1.42
    我
    1.40
    我在
    1.38
     أ
    1.34
     بأ
    1.33
    怀疑
    1.31
    我的
    1.30
    POSITIVE LOGITS
     Freshman
    2.39
     freshman
    2.37
     freshmen
    2.34
     NCAA
    2.32
     fakult
    2.32
     postseason
    2.26
    campus
    2.25
     collegiate
    2.23
     Clemson
    2.23
    本科
    2.18
    Activations Density 0.211%

    No Known Activations