© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 676
    Prev
    Next
    INDEX
    Explanations

    Generic ;

    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
    idays
    1.57
    平日
    1.47
    .'
    1.46
    '-
    1.46
     wilfully
    1.42
     wanna
    1.41
     storylines
    1.40
    maha
    1.39
     suro
    1.39
    地铁
    1.38
    POSITIVE LOGITS
     מי
    1.47
    ر
    1.46
    нет
    1.44
    WithPath
    1.43
    ολ
    1.43
    өт
    1.38
     समाज
    1.38
     הח
    1.37
    Marx
    1.37
     ඇත
    1.36
    Activations Density 0.336%

    No Known Activations