© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3074
    Prev
    Next
    INDEX
    Explanations

    NumPy in Python data science contexts

    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
    KindOfClass
    3.41
    обходимо
    3.25
    𝑬
    3.23
    𝑺
    3.09
    𝓀
    3.07
    𝑵
    2.95
    𝐾
    2.83
    𝑮
    2.79
    𝑨
    2.77
    ल्याण
    2.75
    POSITIVE LOGITS
    s
    5.60
    ০
    4.87
    t
    4.70
    er
    4.56
    י
    4.45
    т
    4.36
    นี่
    4.25
    ా
    4.20
    ು
    4.17
    ا
    4.13
    Activations Density 0.098%

    No Known Activations