© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30032
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "a"

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

    The neuron strongly activates on the indefinite article “a.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     على
    -1.08
     روی
    -0.92
    <bos>
    -0.87
     на
    -0.85
    uids
    -0.84
     auf
    -0.83
     reason
    -0.82
     奶油
    -0.82
    ）：
    -0.82
     על
    -0.80
    POSITIVE LOGITS
     whim
    1.89
     behalf
    1.47
     basis
    1.21
     Friday
    1.12
     ועל
    1.07
     Wednesday
    1.05
     occasions
    1.03
     Thursday
    0.99
     Tuesday
    0.97
    basis
    0.97
    Activations Density 0.036%

    No Known Activations