© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1056
    Prev
    Next
    INDEX
    Explanations

    websites and documentation

    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_13_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
    李
    1.66
    麒
    1.56
    Мар
    1.46
    ペ
    1.45
    藍
    1.45
    Ли
    1.43
    ‌آ
    1.42
    Пі
    1.42
    北京
    1.41
    赵
    1.41
    POSITIVE LOGITS
     Such
    1.02
     Couch
    1.02
     All
    0.99
     Testament
    0.99
     ness
    0.98
     ใด
    0.98
     This
    0.98
     tions
    0.97
     These
    0.97
     CS
    0.93
    Activations Density 0.091%

    No Known Activations