© 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. 14581
    Prev
    Next
    INDEX
    Explanations

    explaining the word in quotes

    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
    ला
    2.82
    u
    2.63
    cardia
    2.61
    cid
    2.44
    מת
    2.38
    houses
    2.37
    مم
    2.33
    ComponentName
    2.33
    ׁ
    2.32
    ர்
    2.30
    POSITIVE LOGITS
    ень
    2.78
    犸
    2.55
    าด
    2.49
     شاء
    2.48
    ストア
    2.44
    𝑡
    2.40
    我覺得
    2.37
    ೆಗೆ
    2.37
     له‌
    2.32
    𝑒
    2.32
    Activations Density 0.022%

    No Known Activations