© 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. 3423
    Prev
    Next
    INDEX
    Explanations

    titles of articles or lectures

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

    The neuron is strongly activated by numeric tokens (e.g. years, page numbers, counts), i.e. it detects 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
    ಂತ
    -0.85
     désigne
    -0.83
     seperti
    -0.77
     chargée
    -0.75
     établie
    -0.72
     présentée
    -0.71
    ifié
    -0.71
    papan
    -0.69
     prévue
    -0.69
    ldots
    -0.69
    POSITIVE LOGITS
     entitled
    7.00
     titled
    6.66
    entitled
    5.13
    titled
    4.94
    Titled
    4.31
     entitle
    3.81
     titulado
    3.81
     intitulé
    3.70
     title
    3.56
     called
    3.52
    Activations Density 0.299%

    No Known Activations