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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8336
    Prev
    Next
    INDEX
    Explanations

    code comments and string literals

    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
    𝐥
    3.26
    𝗹
    3.03
    𝐦
    2.88
    𝐫
    2.82
    𝐭
    2.77
    𝐧
    2.71
    𝐢
    2.70
    𝗺
    2.70
    اً
    2.67
    𝘁
    2.64
    POSITIVE LOGITS
    ಿ
    2.79
    en
    2.78
    에
    2.72
    a
    2.70
    ン
    2.66
    ه
    2.62
    ে
    2.59
    ing
    2.57
    й
    2.51
    に
    2.38
    Activations Density 0.181%

    No Known Activations