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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7539
    Prev
    Next
    INDEX
    Explanations

    place, traditions, families

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

    The neuron fires on words that are valid English homographs—terms that can function both as a noun and as a verb.

    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
    /
    1.12
    C
    0.87
    textrm
    0.82
    0
    0.81
    +/
    0.77
    R
    0.77
    +
    0.73
    č
    0.73
    ™
    0.73
    CAR
    0.71
    POSITIVE LOGITS
     і
    1.25
    і
    1.22
     с
    1.16
     І
    1.15
     incompre
    1.15
     һ
    1.13
     є
    1.11
     merciless
    1.11
     簡単
    1.11
     slander
    1.10
    Activations Density 0.000%

    No Known Activations