© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2236
    Prev
    Next
    INDEX
    Explanations

    electromagnetic fields, interference, and components

    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
    𝙀
    3.12
    𝙍
    2.96
    𝘾
    2.93
    𝙃
    2.86
    𝙔
    2.85
    𝙉
    2.83
    िश्वत
    2.82
    𝙏
    2.81
    𝙄
    2.80
    𝘼
    2.79
    POSITIVE LOGITS
    e
    5.30
    s
    5.01
    ে
    4.84
    sion
    4.72
    a
    4.66
    ০
    4.42
    ه
    4.20
    ి
    3.89
    ी
    3.85
    т
    3.83
    Activations Density 0.514%

    No Known Activations