© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1922
    Prev
    Next
    INDEX
    Explanations

    functional efficiency

    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
    家人
    1.23
     sloth
    1.19
     privado
    1.17
    り
    1.16
     honor
    1.16
     patiently
    1.15
     habitants
    1.13
     Tory
    1.13
     en
    1.11
    てください
    1.10
    POSITIVE LOGITS
    ‌ترین
    1.77
    )^{[\
    1.73
    度和
    1.73
    পূর্ন
    1.72
    >∕
    1.71
    度的
    1.71
    ]]->
    1.68
    >∕</
    1.65
    度は
    1.62
    >[</
    1.60
    Activations Density 0.758%

    No Known Activations