© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4058
    Prev
    Next
    INDEX
    Explanations

    class/module instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     У
    0.67
     Tij
    0.64
     ചെയ്യ
    0.64
    neys
    0.63
    ែម
    0.61
     Kembali
    0.61
    ாயம்
    0.60
     division
    0.58
     Результа
    0.58
     theorem
    0.57
    POSITIVE LOGITS
    Mile
    0.75
    muy
    0.73
    Luckily
    0.72
    {},
    0.72
     lié
    0.72
    像是
    0.72
    Aer
    0.70
    Smartphone
    0.70
     আদর্শ
    0.70
    完美的
    0.69
    Activations Density 0.121%

    No Known Activations