© 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. 30103
    Prev
    Next
    INDEX
    Explanations

    localization Hardy Pond

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

    The neuron activates on numeric constants—i.e. tokens consisting of sequences of digits.

    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
     sitten
    -1.01
    になりますが
    -0.97
     Chapitre
    -0.96
     historie
    -0.94
    になれば
    -0.94
    の効果
    -0.94
     dorada
    -0.93
     botas
    -0.90
     cercan
    -0.90
     kompati
    -0.90
    POSITIVE LOGITS
     Rather
    0.91
     rather
    0.90
    lick
    0.87
    @
    0.86
    问题
    0.85
    が
    0.84
    FUENTES
    0.84
     eenvou
    0.83
     troublesome
    0.82
    itre
    0.82
    Activations Density 0.001%

    No Known Activations