© 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. 3451
    Prev
    Next
    INDEX
    Explanations

    test and testing

    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
    下降
    2.80
    Segoe
    2.57
    র্জাতিক
    2.38
    InnerHTML
    2.36
    AsUp
    2.36
    ई
    2.32
     circuitos
    2.30
    dolo
    2.30
    üedad
    2.28
    ׁ
    2.26
    POSITIVE LOGITS
     abar
    2.07
     scene
    1.93
     govor
    1.91
    စီ
    1.88
    зі
    1.86
     wav
    1.84
     lep
    1.82
    센
    1.80
    Dos
    1.74
     دان
    1.74
    Activations Density 0.063%

    No Known Activations