© 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. 1643
    Prev
    Next
    INDEX
    Explanations

    numbers and currency ranges

    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
    िक्शन
    3.06
    स्कृत
    3.00
    ifizierung
    2.92
    価
    2.91
    ificación
    2.87
    Dv
    2.87
    導數
    2.86
    िक्ट
    2.83
     пое
    2.79
    एं
    2.79
    POSITIVE LOGITS
    ly
    4.08
    gggg
    3.28
    ggg
    3.11
    th
    2.52
    st
    2.43
    gly
    2.40
    ing
    2.35
    doll
    2.29
    ת
    2.27
    ness
    2.20
    Activations Density 0.585%

    No Known Activations