© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2442
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on multi-syllable descriptive adjectives (e.g. “accepted,” “fiscal,” “decorative,” “ovate,” “compact”).

    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
    btnInventory
    0.44
    अप्रैल
    0.43
    ৩৯
    0.43
    ೃಹ
    0.42
    ۃ
    0.42
    我们在
    0.42
    ัตว์
    0.41
    东
    0.41
    贰百
    0.41
    RichEmbed
    0.41
    POSITIVE LOGITS
     disso
    0.57
     estar
    0.54
     andere
    0.48
     outra
    0.47
     estiver
    0.47
     Wenn
    0.45
     wrongdoing
    0.45
     olmayan
    0.44
     esta
    0.44
     cette
    0.44
    Activations Density 0.000%

    No Known Activations