© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    However, followed by explanation

    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
    ي
    3.85
    ا
    3.38
    هو
    3.17
    اا
    2.99
    ו
    2.95
    고
    2.91
    ب
    2.85
    iul
    2.80
    ぉ
    2.79
    y
    2.78
    POSITIVE LOGITS
    Pa
    2.52
    QU
    2.30
    igate
    2.20
    ПА
    2.06
    JO
    2.04
    噌
    2.03
    PUB
    2.03
    𝙎
    2.01
    Va
    2.00
    acre
    1.98
    Activations Density 0.058%

    No Known Activations