© 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. 13375
    Prev
    Next
    INDEX
    Explanations

    understanding why

    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
    ರ್‌
    1.74
    oxylated
    1.73
    воря
    1.71
    里斯
    1.65
     Coatings
    1.61
     wiring
    1.60
    ⟨
    1.60
     Эр
    1.59
    ᱽ
    1.58
    腊
    1.54
    POSITIVE LOGITS
    ku
    1.82
    '"
    1.74
    "'
    1.67
    ";
    1.67
    "...
    1.66
    Agenda
    1.63
    ূর্তি
    1.62
    embers
    1.59
    。"
    1.58
    uus
    1.57
    Activations Density 0.020%

    No Known Activations