© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1648
    Prev
    Next
    INDEX
    Explanations

    any specific

    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_17_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
    jahter
    0.89
     непло
    0.87
    答应
    0.81
    笑顔
    0.79
    ocarbon
    0.78
    relsen
    0.78
    ok
    0.77
     ҡ
    0.75
    WarningLevel
    0.75
    shah
    0.74
    POSITIVE LOGITS
     specific
    4.27
    specific
    3.97
     Specific
    3.86
     particular
    3.85
    Specific
    3.70
     spécifique
    3.63
     específico
    3.62
     special
    3.61
     específica
    3.55
    特定的
    3.52
    Activations Density 2.795%

    No Known Activations