© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    qualifying descriptive words

    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
    nya
    5.66
    了
    5.00
    ्स
    4.99
    น่า
    4.83
    د
    4.76
    นี
    4.43
    sg
    4.38
    ので
    4.32
    น
    4.32
    น้อย
    4.30
    POSITIVE LOGITS
    깐
    3.93
    লাষ
    3.60
    ppets
    3.42
    ゃ
    3.25
    ਆ
    3.21
    য়া
    3.16
    деся
    3.12
    ễm
    3.09
    ểm
    3.08
    athermy
    2.98
    Activations Density 2.712%

    No Known Activations