© 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. 14924
    Prev
    Next
    INDEX
    Explanations

    camera system

    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
    ric
    1.51
    ic
    1.46
    福
    1.41
    sac
    1.38
     sac
    1.37
    कारी
    1.30
    cot
    1.27
    膠
    1.27
    絕
    1.26
    oxic
    1.24
    POSITIVE LOGITS
    ליה
    1.62
     Thereby
    1.61
    FromServer
    1.60
     Afterwards
    1.59
     méridionale
    1.58
    Zespół
    1.56
    Collected
    1.55
    Amid
    1.55
     مورد
    1.55
    Depart
    1.52
    Activations Density 0.125%

    No Known Activations