© 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. 40104
    Prev
    Next
    INDEX
    Explanations

    programming languages and concepts

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

    This neuron spots numeric tokens (numbers and numeric literals) 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
    ө
    -0.87
    chema
    -0.85
    rights
    -0.84
    StartsWith
    -0.81
    stand
    -0.81
    grant
    -0.81
     sini
    -0.81
     toer
    -0.79
    érale
    -0.79
    supply
    -0.79
    POSITIVE LOGITS
     frutta
    0.92
     Trello
    0.87
    atterns
    0.84
     könny
    0.82
     entdeckt
    0.82
     JBL
    0.82
     spearheaded
    0.81
     probiotics
    0.80
     mittler
    0.80
     privilégi
    0.80
    Activations Density 0.002%

    No Known Activations