© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15260
    Prev
    Next
    INDEX
    Explanations

    metro metropolitan

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     tekan
    0.60
    掉了
    0.59
    అ
    0.53
     преда
    0.52
     ஆண்டுகளுக்கு
    0.52
     ボタン
    0.50
    ⇑
    0.50
    大大
    0.49
     &$\
    0.49
    ajaan
    0.49
    POSITIVE LOGITS
    opolitan
    0.88
     Metro
    0.84
    plit
    0.82
    plex
    0.80
    ropolitan
    0.79
    PCS
    0.78
     polit
    0.77
     Metropolitan
    0.77
     metro
    0.76
    Metro
    0.76
    Activations Density 0.010%

    No Known Activations