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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12701
    Prev
    Next
    INDEX
    Explanations

    thought-provoking concepts

    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
    e
    3.35
    eek
    3.23
    eed
    3.10
    에
    3.01
    יים
    3.01
    hlas
    2.98
    ಯಲ್ಲಿ
    2.91
    yata
    2.91
    erden
    2.88
    utzen
    2.87
    POSITIVE LOGITS
     hecho
    2.75
    constraintTop
    2.52
    خدام
    2.49
     sentido
    2.44
    хран
    2.40
    ┈┈
    2.39
     связи
    2.33
     passare
    2.32
    usescu
    2.32
    ☰
    2.30
    Activations Density 0.023%

    No Known Activations