© 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. 464
    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
    ikul
    0.76
    asyonu
    0.73
    acionais
    0.72
    ுக்
    0.72
    omized
    0.71
    힣
    0.71
     urmă
    0.71
    upart
    0.71
     loudness
    0.70
    ivated
    0.70
    POSITIVE LOGITS
    ما
    0.92
    Ла
    0.89
    NGC
    0.87
    Ф
    0.86
    М
    0.85
    С
    0.85
    Пер
    0.84
    Ка
    0.81
    Ма
    0.80
    Га
    0.79
    Activations Density 0.604%

    No Known Activations