© 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. 79553
    Prev
    Next
    INDEX
    Explanations

    schools and colleges

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

    The neuron activates on numeric tokens (especially years or other standalone numbers).

    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
     presided
    -0.87
    Jain
    -0.82
    posable
    -0.77
    پیش
    -0.77
    選び
    -0.76
     Breen
    -0.76
    ༻
    -0.76
    QRCode
    -0.75
    Suisse
    -0.75
     chaired
    -0.74
    POSITIVE LOGITS
    Term
    0.91
     Term
    0.89
     term
    0.84
     fag
    0.79
    dding
    0.74
    教材
    0.73
     Double
    0.72
     concent
    0.71
     div
    0.70
    有没有
    0.70
    Activations Density 0.025%

    No Known Activations