© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    Japanese otaku or approximations

    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
    leri
    3.19
    蜍
    2.78
    ('.')[
    2.74
    lerle
    2.71
    𝗻
    2.68
    𝗲
    2.61
    lerinin
    2.51
    árny
    2.48
    arzys
    2.46
    tedir
    2.46
    POSITIVE LOGITS
    м
    3.89
    Zitat
    3.32
    ۰
    3.22
    ر
    3.05
    ని
    2.98
    валь
    2.97
    𝑜
    2.90
    р
    2.85
    ва
    2.83
    ร์
    2.78
    Activations Density 0.262%

    No Known Activations