© 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. 1026
    Prev
    Next
    INDEX
    Explanations

    mirror neurons fire

    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
    :
    0.75
    office
    0.75
     $\
    0.73
    _
    0.72
    »:
    0.71
     :
    0.71
     office
    0.70
     <
    0.69
    1
    0.69
    ...@
    0.67
    POSITIVE LOGITS
     oltre
    1.60
     sowie
    1.55
     Selain
    1.54
    Selain
    1.51
     serta
    1.48
     valamint
    1.48
     nonostante
    1.45
     tandis
    1.45
     ebenso
    1.43
     mentre
    1.43
    Activations Density 0.339%

    No Known Activations