© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 41
    Prev
    Next
    INDEX
    Explanations

    ' followed by s

    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
     Trời
    1.22
    ្អ
    1.14
    lineTo
    1.13
     (^{
    1.12
     (^
    1.10
    ອນ
    1.09
    slideClass
    1.08
     disposition
    1.05
     hotly
    1.04
    scriptstyle
    1.04
    POSITIVE LOGITS
    ↵↵
    1.23
    、、
    0.98
    Zitat
    0.93
     yakni
    0.93
    ↵
    0.92
    o
    0.92
     เส
    0.90
    ↳
    0.89
    ↵↵↵
    0.89
    お知らせ
    0.86
    Activations Density 1.489%

    No Known Activations