© 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. 106461
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    The neuron detects tokens composed of or containing numerical digits (i.e. number tokens).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ####
    -0.84
    NUMBER
    -0.82
     TY
    -0.79
     notas
    -0.77
     needed
    -0.77
    Discover
    -0.77
    setForm
    -0.76
     Note
    -0.75
     vatt
    -0.75
     Received
    -0.74
    POSITIVE LOGITS
     nedeniyle
    0.82
    edakan
    0.79
    それに
    0.77
     rijk
    0.77
     bodybuilding
    0.77
     agregar
    0.76
     autoestima
    0.76
     gemaakt
    0.76
     Additions
    0.75
    Barg
    0.74
    Activations Density 0.001%

    No Known Activations