© 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. 2606
    Prev
    Next
    INDEX
    Explanations

    far beyond

    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
    صاب
    2.36
    껍
    2.36
    hardhat
    2.34
    cores
    2.31
    جی
    2.27
    macher
    2.25
    cored
    2.25
    mousePressed
    2.23
    uaikan
    2.22
    NC
    2.15
    POSITIVE LOGITS
     afield
    3.41
    ্স্ট
    3.12
    𝗼
    2.66
    erà
    2.65
    ас
    2.59
    𝐨
    2.59
     chronological
    2.56
    ор
    2.56
    о
    2.55
    EqualTo
    2.50
    Activations Density 0.081%

    No Known Activations