© 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. 22-GEMMASCOPE-RES-131K
    7. 35356
    Prev
    Next
    INDEX
    Explanations

    specific entities and their continuations

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

    This neuron activates on short alphanumeric tokens—especially numbers, version identifiers, and brief uppercase codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     luat
    -1.03
    sibilità
    -1.01
     maquillage
    -1.01
    ！】
    -0.99
     llegue
    -0.94
    atterson
    -0.94
    ͬ
    -0.94
    푠
    -0.92
     disappoint
    -0.92
     femininos
    -0.92
    POSITIVE LOGITS
     then
    1.05
     different
    0.97
     anzunehmen
    0.94
    then
    0.92
    H
    0.91
     would
    0.89
    R
    0.87
    V
    0.86
     "",
    0.86
    M
    0.85
    Activations Density 0.061%

    No Known Activations