© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    dynamic, vibrant descriptions

    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
    िप्स
    3.10
    ੀ
    3.01
    इ
    3.00
    ívá
    2.80
    ی
    2.79
    िनय
    2.74
    ECTORS
    2.69
    rebbe
    2.68
    сибо
    2.66
    ियों
    2.65
    POSITIVE LOGITS
    ed
    2.85
    ة
    2.84
    bod
    2.23
    maßen
    2.19
    nett
    2.14
    ра
    2.09
     offsetting
    2.08
    puted
    2.07
     reck
    2.07
    bert
    2.06
    Activations Density 0.074%

    No Known Activations