© 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. 99194
    Prev
    Next
    INDEX
    Explanations

    census-designated place

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

    The neuron specifically fires on multi‐digit numeric tokens (e.g. case numbers, years, large numerals).

    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
    mojo
    -0.81
     förra
    -0.78
    dart
    -0.78
     anledning
    -0.77
     Éditions
    -0.77
    wsgi
    -0.76
    WindowSize
    -0.75
    IUrlHelper
    -0.75
    cznych
    -0.75
    rdom
    -0.74
    POSITIVE LOGITS
     Bergen
    0.96
    Bergen
    0.92
     education
    0.84
    Crit
    0.83
     bergen
    0.77
    volezza
    0.77
     VD
    0.75
    を広
    0.75
    วก
    0.75
    Materia
    0.74
    Activations Density 0.000%

    No Known Activations