© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3345
    Prev
    Next
    INDEX
    Explanations

    smithsonianmag.com/science-nature

    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
    webserv
    1.52
    ी
    1.38
    יים
    1.38
    ComponentName
    1.34
    keits
    1.32
    quela
    1.31
    houd
    1.29
    isasi
    1.28
    ি
    1.27
    িও
    1.27
    POSITIVE LOGITS
     ex
    1.37
     তুল
    1.36
    Ex
    1.34
    нам
    1.33
     Ex
    1.33
    roy
    1.28
    ỉnh
    1.27
    ゥム
    1.26
    xFFFF
    1.23
    rai
    1.23
    Activations Density 0.070%

    No Known Activations