© 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. 79317
    Prev
    Next
    INDEX
    Explanations

    soap opera Hollyoaks and River City

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

    The neuron strongly activates on numeric tokens—especially four-digit year-like 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
     Behavioral
    -0.87
    ӱ
    -0.77
    Behavioral
    -0.76
     polarized
    -0.75
    жі
    -0.73
    ename
    -0.73
    Tổng
    -0.72
    军团
    -0.71
    staticmethod
    -0.70
    ാൻ
    -0.70
    POSITIVE LOGITS
     Emmer
    1.20
     soap
    1.01
    Holly
    0.86
    soap
    0.86
     Holly
    0.84
     Soap
    0.84
     holly
    0.83
    Soap
    0.82
     omnibus
    0.82
     Coronation
    0.81
    Activations Density 0.025%

    No Known Activations