© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7924
    Prev
    Next
    INDEX
    Explanations

    states and their entities

    np_acts-logits-general · gemini-2.5-flash-lite

    us states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    市内
    0.42
    Mayor
    0.42
     harbour
    0.40
     市
    0.39
     இலங்கை
    0.39
     Mayor
    0.39
     मेयर
    0.39
     Bağ
    0.39
     मलेशिया
    0.38
     المدينة
    0.38
    POSITIVE LOGITS
     statewide
    0.97
    州
    0.94
    州的
    0.93
     Statewide
    0.91
     மாநிலத்தில்
    0.84
     Legislature
    0.82
     legislature
    0.77
     governor
    0.75
     state
    0.73
     Governor
    0.73
    Activations Density 0.145%

    No Known Activations