© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57847
    Prev
    Next
    INDEX
    Explanations

    Redistributions of source code

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

    The neuron strongly activates on tokens containing numbers or numeric characters (e.g., version numbers, years, digit sequences).

    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
     exten
    -0.92
    MPI
    -0.82
    IFont
    -0.80
    setRequest
    -0.77
     mobi
    -0.76
     MPI
    -0.75
    Hose
    -0.75
     Principal
    -0.73
    Principal
    -0.72
     Slu
    -0.72
    POSITIVE LOGITS
    ättern
    0.81
     Kim
    0.71
    Pack
    0.66
    czyna
    0.65
    Kim
    0.64
     specifically
    0.63
    乃至
    0.61
     proportionality
    0.61
     considerada
    0.61
     wrote
    0.60
    Activations Density 0.077%

    No Known Activations