© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14167
    Prev
    Next
    INDEX
    Explanations

    data privacy laws

    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
    i
    1.75
    ancher
    1.38
     نظر
    1.37
     recruit
    1.36
    uix
    1.35
    UTER
    1.30
    iou
    1.30
    ARP
    1.29
    anol
    1.29
    aner
    1.29
    POSITIVE LOGITS
    ٹی
    2.14
    朽
    2.01
    皑
    1.96
     സോ
    1.95
     શ્રી
    1.93
    )}^{
    1.91
     Erde
    1.91
    日まで
    1.91
     वैदिक
    1.90
    ța
    1.89
    Activations Density 0.000%

    No Known Activations