© 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. 14469
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts

    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
     單
    1.92
     也
    1.83
     因此
    1.82
     Trên
    1.81
     而且
    1.80
     跟
    1.79
     嗯
    1.78
     ſ
    1.78
     此
    1.77
     然而
    1.76
    POSITIVE LOGITS
    sit
    1.51
    d
    1.45
    ab
    1.38
    ointing
    1.38
    dak
    1.36
    ov
    1.34
    lav
    1.32
    mek
    1.32
    av
    1.31
    im
    1.31
    Activations Density 0.319%

    No Known Activations