© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14243
    Prev
    Next
    INDEX
    Explanations

    align with their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     jammed
    1.96
     자동차
    1.89
     이하
    1.86
     hold
    1.83
     certi
    1.83
     車
    1.80
    𝘯
    1.80
     証明
    1.79
     通
    1.78
     车
    1.77
    POSITIVE LOGITS
    传统
    2.04
    ёнок
    1.99
    Ар
    1.98
     tradicion
    1.97
     традиции
    1.95
    性と
    1.94
    ኼ
    1.94
     prestigio
    1.93
    经典
    1.90
     autoestima
    1.89
    Activations Density 0.059%

    No Known Activations