© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10555
    Prev
    Next
    INDEX
    Explanations

    keep followed by advice

    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_13_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
    म
    2.57
    𝙧
    2.29
    𝙚
    2.26
    𝙞
    2.16
    getQuery
    2.14
    
    2.08
    u
    2.07
    𝙩
    2.06
    ক্ষ
    2.03
    𝗮
    2.03
    POSITIVE LOGITS
    ders
    2.49
    ς
    2.42
    ücht
    2.32
    ுள்ளார்
    2.26
    dzić
    2.22
    ுள்ள
    2.19
     aperiam
    2.10
    plicial
    2.06
    ೆಯ
    2.03
    din
    2.02
    Activations Density 0.051%

    No Known Activations