© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1180
    Prev
    Next
    INDEX
    Explanations

    remarkably, especially, muitas, sangat

    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_13_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
     esistono
    0.86
    inale
    0.85
     want
    0.84
    (
    0.83
     John
    0.80
     need
    0.78
     normalement
    0.78
     exists
    0.78
     bet
    0.77
     Suppose
    0.77
    POSITIVE LOGITS
     culminated
    1.67
    특히
    1.66
     soprattutto
    1.62
     특히
    1.57
     รวมถึง
    1.54
     덕
    1.53
     zudem
    1.51
     także
    1.50
    尤其
    1.49
     culmin
    1.49
    Activations Density 1.257%

    No Known Activations