© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1773
    Prev
    Next
    INDEX
    Explanations

    what is a

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

    This neuron fires on definitional sentences that start with a proper name or term followed by “is a,” i.e. it detects patterns like “X is a ….”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    z
    0.64
    c
    0.64
    j
    0.60
     this
    0.59
    this
    0.58
    i
    0.57
     theſe
    0.56
    v
    0.55
    k
    0.55
    vv
    0.54
    POSITIVE LOGITS
     multifaceted
    0.73
     epitome
    0.66
     milestone
    0.63
     nonfiction
    0.63
     unisex
    0.63
     quintessential
    0.62
     purported
    0.61
     nonprofit
    0.61
     descendant
    0.61
     automobile
    0.59
    Activations Density 0.087%

    No Known Activations