© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10852
    Prev
    Next
    INDEX
    Explanations

    4CAF50

    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_22_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
     оценки
    0.89
     గత
    0.87
    cparam
    0.85
     कृत
    0.83
     あれ
    0.82
     помощью
    0.82
     ลอง
    0.81
    ベ
    0.81
     (...
    0.80
    рты
    0.79
    POSITIVE LOGITS
    CCCCCC
    1.02
    EEEE
    0.97
    FFF
    0.93
     abhängig
    0.91
     Syllabus
    0.89
    FFFF
    0.88
     jederzeit
    0.88
     alltid
    0.87
    CCCC
    0.87
    FFFFFF
    0.87
    Activations Density 0.007%

    No Known Activations