© 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. 973
    Prev
    Next
    INDEX
    Explanations

    LaTeX equation environments

    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
    ῥ
    1.49
    iezan
    1.42
     ake
    1.42
    údo
    1.37
    ृती
    1.37
    orado
    1.34
     idha
    1.33
    peł
    1.28
    enchymal
    1.27
    össä
    1.27
    POSITIVE LOGITS
     roh
    0.90
     '
    0.87
    ார்
    0.85
    at
    0.85
     ground
    0.85
     right
    0.83
    <bos>
    0.82
    ![
    0.82
    www
    0.80
     d
    0.79
    Activations Density 0.328%

    No Known Activations