© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14617
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    τας
    2.18
    дцать
    2.18
    𝗮
    2.06
    iasis
    2.04
    စိတ်အပိုင်း
    2.02
    ordinate
    2.00
    ارع
    1.95
    antam
    1.87
    anele
    1.87
    arul
    1.81
    POSITIVE LOGITS
    ⎪
    2.38
    য়ের
    2.29
    itian
    2.28
    ił
    2.27
    য়ের
    2.25
    হ
    2.24
     উঠ
    2.21
     convexo
    2.16
     উপায়
    2.16
     badań
    2.13
    Activations Density 0.019%

    No Known Activations