© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5748
    Prev
    Next
    INDEX
    Explanations

    Snowflake

    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
    gı
    2.40
    𝘭
    2.31
    pat
    2.25
    ۷
    2.22
    ا
    2.14
    enschaft
    2.11
    符
    2.11
     karya
    2.11
    ıldı
    2.10
    প্ট
    2.10
    POSITIVE LOGITS
    Years
    2.33
    UCLE
    2.28
     मांसपेशियों
    2.17
     raises
    2.16
    dS
    2.10
     lumens
    2.05
    AndKeys
    2.02
    {,}
    2.00
    ુપ
    1.97
    getParent
    1.97
    Activations Density 0.115%

    No Known Activations