© 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. 778
    Prev
    Next
    INDEX
    Explanations

    Slovak and glutamate

    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
    ي
    3.05
    ం
    2.68
    ಿ
    2.65
    る
    2.57
     instalment
    2.51
     installment
    2.46
    া
    2.45
    ه
    2.35
    ו
    2.33
     sourceType
    2.28
    POSITIVE LOGITS
    ≤</
    2.46
    燵
    2.45
    躇
    2.44
    ากหลาย
    2.40
    逅
    2.39
    瑯
    2.37
    蒻
    2.32
    koľ
    2.27
    ricted
    2.25
    道府県
    2.25
    Activations Density 1.777%

    No Known Activations