© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5094
    Prev
    Next
    INDEX
    Explanations

    vapor compression

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

    The neuron selectively activates on words or names beginning with the letter “V,” especially proper nouns and titles starting with “V.”

    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_31_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
    𝙣
    0.66
    𝙩
    0.66
    卟
    0.66
    ⑹
    0.64
     bessere
    0.62
     здравоохранения
    0.60
     vuelo
    0.60
    bewegung
    0.60
     बेहतर
    0.59
     venced
    0.59
    POSITIVE LOGITS
     vya
    0.75
    IMPORTANT
    0.70
    Vin
    0.65
     IMPORTANT
    0.65
     V
    0.64
    Vest
    0.63
     Vik
    0.61
     Vital
    0.60
     Voc
    0.59
     Vault
    0.59
    Activations Density 0.666%

    No Known Activations