© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    code blocks and formatting

    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
    فت
    2.31
    ़
    2.10
    到一个
    2.05
    ۜ
    2.03
    ोजन
    2.00
    uduk
    1.99
    
    1.99
    ্লেখ
    1.97
     বিভাগের
    1.96
    projectlombok
    1.94
    POSITIVE LOGITS
    _^
    2.91
    ᵏ
    2.62
    𝓛
    2.24
    upné
    2.22
    𝓜
    2.22
    🆁
    2.21
    壤
    2.19
    წიფ
    2.17
    Foo
    2.16
    ಖ್ಯ
    2.15
    Activations Density 0.056%

    No Known Activations