© 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. 1451
    Prev
    Next
    INDEX
    Explanations

    data science analysis collection

    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
    mers
    3.35
    了
    3.03
    tf
    2.78
    ことができる
    2.78
    től
    2.71
    ]".
    2.67
    tis
    2.61
     marcha
    2.61
     "+
    2.59
    sl
    2.58
    POSITIVE LOGITS
    ার্টমেন্ট
    2.67
    ffer
    2.51
    SqlClient
    2.22
    引き
    2.16
    res
    2.16
     Verarbeitung
    2.10
    يبة
    2.07
    훨
    2.06
    렁
    2.05
    ෙස
    2.04
    Activations Density 0.060%

    No Known Activations