© 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. 13432
    Prev
    Next
    INDEX
    Explanations

    code, URLs, or special characters

    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
    s
    4.17
    ات
    3.31
    sapp
    2.96
    sle
    2.88
    sley
    2.83
    sb
    2.73
    sning
    2.71
    safe
    2.70
    t
    2.69
    sac
    2.66
    POSITIVE LOGITS
    par
    2.82
    Par
    2.79
    
    2.75
    მწიფ
    2.66
    Wings
    2.56
    ALTERNATIVNAMEN
    2.55
    ரஜன்
    2.50
    ط
    2.47
    𝗆
    2.46
    anyahu
    2.44
    Activations Density 0.011%

    No Known Activations