© 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. 106200
    Prev
    Next
    INDEX
    Explanations

    German television series

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

    The neuron strongly activates on standalone numeric tokens (e.g. literal numbers or numeric identifiers) in both prose and code.

    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
     Primary
    -0.67
    调
    -0.67
     princípios
    -0.67
    ((&
    -0.65
     primary
    -0.64
    comun
    -0.63
    TableAdapter
    -0.63
    chnen
    -0.63
     stampa
    -0.62
     comienzos
    -0.62
    POSITIVE LOGITS
    🏒
    0.75
    meneu
    0.67
    ladora
    0.66
    喜
    0.66
     LUMP
    0.66
    氐
    0.65
    港
    0.65
    ikbaar
    0.62
     港
    0.62
    drawString
    0.62
    Activations Density 0.084%

    No Known Activations