© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 234
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     представлены
    1.07
    은
    1.01
     протягом
    1.00
    および
    0.99
     uchun
    0.98
     учун
    0.97
     respectivamente
    0.97
    yfikacji
    0.96
    начально
    0.95
    は
    0.93
    POSITIVE LOGITS
     being
    3.23
     having
    3.07
     getting
    2.96
     seeing
    2.78
     doing
    2.74
     owning
    2.69
     putting
    2.65
    being
    2.63
    having
    2.56
     taking
    2.56
    Activations Density 8.612%

    No Known Activations