© 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. 14452
    Prev
    Next
    INDEX
    Explanations

    concept definitions

    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
     其他
    3.53
     少
    3.40
     中央
    3.38
     修改
    3.34
     其
    3.17
     南
    3.16
     인천
    3.11
     除了
    3.06
     沙
    3.06
     市
    3.04
    POSITIVE LOGITS
    ë
    2.79
    Lä
    2.79
    autant
    2.76
    Gambar
    2.60
    ultimo
    2.59
    controle
    2.55
    và
    2.53
    ultima
    2.52
    હ
    2.52
    evento
    2.50
    Activations Density 0.028%

    No Known Activations