© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10917
    Prev
    Next
    INDEX
    Explanations

    low vs high effort/risk

    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_13_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
    了
    6.08
    nya
    5.83
    ly
    5.46
    います
    4.91
    r
    4.63
    ्स
    4.50
    st
    4.15
    اً
    3.96
    ことが
    3.93
    다고
    3.92
    POSITIVE LOGITS
    pportun
    3.83
    pportunities
    3.77
    ؤں
    3.52
    ٔ
    3.52
    pee
    3.44
    ğlu
    3.43
    cean
    3.33
    pped
    3.20
    ה
    3.14
    ppy
    3.14
    Activations Density 1.410%

    No Known Activations