© 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. 13984
    Prev
    Next
    INDEX
    Explanations

    what you've got

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

    The neuron specifically detects occurrences of the contraction "'ve" (as in I've, you’ve, we’ve) in the text.

    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
     an
    1.01
     not
    0.93
     a
    0.85
    了一个
    0.85
    not
    0.83
     credence
    0.74
     auspices
    0.73
     NOT
    0.72
    了一個
    0.72
     instincts
    0.71
    POSITIVE LOGITS
    ioxid
    0.68
    Got
    0.65
     gotta
    0.65
     주는
    0.65
    ၇
    0.64
     Потом
    0.63
    DesignTime
    0.62
    где
    0.61
    azem
    0.61
    Ethnic
    0.61
    Activations Density 0.125%

    No Known Activations