© 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. 99207
    Prev
    Next
    INDEX
    Explanations

    names and labels

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

    The neuron strongly activates on numeric tokens—years, model/reference numbers, and other 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
     DVDs
    -0.81
     Kawasaki
    -0.80
     ২০১
    -0.79
     Hennessy
    -0.75
    elevation
    -0.73
     Johnnie
    -0.72
    rum
    -0.72
    𝐮
    -0.71
     volk
    -0.71
    ??"
    -0.71
    POSITIVE LOGITS
     case
    0.82
     cases
    0.80
     fruity
    0.77
     markets
    0.76
     radium
    0.74
     restauración
    0.71
    出張
    0.71
     scholars
    0.71
     Fellows
    0.70
     Extract
    0.70
    Activations Density 0.013%

    No Known Activations