© 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. 130
    Prev
    Next
    INDEX
    Explanations

    time, under, Required, Treasury, HAN

    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
    例文帳に追加
    1.88
    s
    1.79
    ンダー
    1.73
    sj
    1.67
    Rabbit
    1.65
     Everywhere
    1.58
     例文帳に追加
    1.54
    ண்முக
    1.53
    BackColor
    1.50
    sion
    1.50
    POSITIVE LOGITS
    ഛ
    1.73
     Megh
    1.66
     ثبت
    1.61
     minh
    1.60
     jonka
    1.59
     neler
    1.58
     Klav
    1.57
     dik
    1.54
     prav
    1.54
    anjutnya
    1.53
    Activations Density 0.000%

    No Known Activations