© 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. 66629
    Prev
    Next
    INDEX
    Explanations

    length description

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

    The neuron activates on standalone numeric tokens (integer values) within 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
    $
    -2.81
    -
    -2.08
     a
    -2.00
     now
    -1.80
    :
    -1.78
    '
    -1.78
    te
    -1.65
     all
    -1.61
    {
    -1.61
     this
    -1.60
    POSITIVE LOGITS
    鴞
    1.85
    ⮜
    1.84
     repuesto
    1.84
    ţiei
    1.75
     vlasy
    1.73
    !");
    1.70
     betale
    1.66
    氳
    1.64
     horarios
    1.64
    '];
    1.64
    Activations Density 0.001%

    No Known Activations