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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 610
    Prev
    Next
    INDEX
    Explanations

    sections and titles

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

    The neuron fires on numeric tokens, i.e. it detects numbers in the text.

    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
    橚
    -1.08
    有一些
    -1.05
     they
    -1.02
    укра
    -0.99
     accessibles
    -0.96
    inheritDoc
    -0.94
    rá
    -0.91
    这是一个
    -0.91
     Frédéric
    -0.91
    tp
    -0.91
    POSITIVE LOGITS
     überras
    1.06
    ayuno
    1.02
     ebenso
    1.01
     with
    0.98
    salomon
    0.96
    ⎩
    0.93
    ingreso
    0.93
     rodeado
    0.92
    nikon
    0.92
     얻
    0.91
    Activations Density 0.152%

    No Known Activations