© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99312
    Prev
    Next
    INDEX
    Explanations

    since 3

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

    The neuron activates on numeric tokens—i.e. any sequences of digits such as version numbers, dates, parameter indices, or other numerical literals.

    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
     Mancini
    -0.79
     река
    -0.75
     norman
    -0.73
    סים
    -0.72
     venus
    -0.71
     шоколад
    -0.71
    ząd
    -0.70
     зависи
    -0.69
    Shim
    -0.69
    Norman
    -0.69
    POSITIVE LOGITS
    DbContext
    0.74
    files
    0.66
     kaarangay
    0.65
     Aussch
    0.65
    ẩy
    0.65
     Trailer
    0.64
    aima
    0.64
    igay
    0.64
     noqa
    0.64
     better
    0.64
    Activations Density 0.069%

    No Known Activations