© 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. 14711
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    nels
    2.36
    啉
    2.25
    baran
    2.16
    erunner
    2.14
    فوظ
    2.14
    쌉
    2.14
    咛
    2.11
    法施行令
    2.09
    gelopen
    2.05
    ្ខ
    2.02
    POSITIVE LOGITS
     yaş
    2.39
    addContainerGap
    2.39
    rover
    2.32
    ໃຊ້
    2.32
    ϻ
    2.28
    ros
    2.27
    Arkadaşlar
    2.27
    beats
    2.27
    rovers
    2.25
    นา
    2.19
    Activations Density 0.023%

    No Known Activations