© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14500
    Prev
    Next
    INDEX
    Explanations

    Clear format

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on semantically salient content words—particularly nouns and adjectives carrying key informational weight—rather than on common function words.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     envelopp
    0.82
     IUCN
    0.78
    IDAD
    0.77
    ladi
    0.77
     CYAN
    0.77
     CENTERS
    0.75
    IANS
    0.75
    အတွင်း
    0.72
    佬
    0.71
     postérieurs
    0.70
    POSITIVE LOGITS
    те
    0.95
    та
    0.79
    ล
    0.79
    ori
    0.79
    га
    0.77
    ș
    0.77
    пе
    0.77
    ivă
    0.75
     sử
    0.75
    т
    0.75
    Activations Density 0.000%

    No Known Activations