© 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. 47300
    Prev
    Next
    INDEX
    Explanations

    genetic study

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

    timestamps or numeric sequences formatted with colons or periods.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    This neuron activates on numeric tokens—especially digit sequences like timecodes, numeric literals, and other multi-digit strings.

    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
     effective
    -1.15
     ручки
    -0.98
    nois
    -0.94
     reciclado
    -0.90
    harmed
    -0.90
     saar
    -0.90
     significant
    -0.85
    冥
    -0.85
    liciter
    -0.84
     other
    -0.82
    POSITIVE LOGITS
     opulent
    0.93
    ungsver
    0.93
     umm
    0.93
    hôpital
    0.92
     Questo
    0.90
    tivamente
    0.90
     ayudará
    0.90
     Beautifully
    0.90
     ROE
    0.89
    Agrade
    0.88
    Activations Density 0.001%

    No Known Activations