© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14692
    Prev
    Next
    INDEX
    Explanations

    crisis support resources

    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
    <start_of_image>
    1.30
     নিয়েই
    1.24
    acher
    1.13
     wichtigsten
    1.07
     genannten
    1.05
    াকৃত
    1.05
    っぱ
    1.03
     Synchron
    1.03
    <strong>
    1.03
    anskje
    1.03
    POSITIVE LOGITS
     박
    1.47
     ق
    1.40
     강
    1.40
     해
    1.32
     кү
    1.32
     نمونه
    1.29
     美
    1.29
     카드
    1.28
     沙
    1.26
     양
    1.24
    Activations Density 0.007%

    No Known Activations