© 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. 475
    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
     exotic
    0.84
    <unused1061>
    0.79
    <unused689>
    0.78
    <unused202>
    0.75
    <unused2125>
    0.75
     prehistoric
    0.75
    <unused150>
    0.75
     ridiculous
    0.74
     opulent
    0.74
    <unused2130>
    0.74
    POSITIVE LOGITS
     pohy
    0.86
     interfaz
    0.86
     flusso
    0.85
     funkcji
    0.84
     configurações
    0.83
     hệ
    0.82
     erő
    0.80
     hareket
    0.80
     cấu
    0.80
     স্থিত
    0.80
    Activations Density 1.136%

    No Known Activations