© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10252
    Prev
    Next
    INDEX
    Explanations

    job search and salary sites

    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_22_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
     falleció
    1.08
    後期
    0.98
     died
    0.95
    퐈
    0.94
    सोशल
    0.93
    retired
    0.92
     Retired
    0.92
    died
    0.89
    hopefully
    0.89
     diagnosed
    0.88
    POSITIVE LOGITS
     ريد
    0.94
    DomainMask
    0.86
     ร
    0.84
     wyr
    0.84
     acaso
    0.82
    แน
    0.82
     dispuestos
    0.82
     interloc
    0.79
     নিক
    0.78
     enclosing
    0.78
    Activations Density 0.122%

    No Known Activations