© 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. 67605
    Prev
    Next
    INDEX
    Explanations

    listing pages

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

    The main thing this neuron does is detect numeric tokens (numbers).

    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
    Incl
    -0.79
    rierten
    -0.75
     pregunto
    -0.75
    ensioni
    -0.71
    pertina
    -0.69
    incorpor
    -0.69
     diría
    -0.69
    nith
    -0.68
     directos
    -0.68
     esenciales
    -0.68
    POSITIVE LOGITS
     ヴィンテージ
    0.78
    Ɛ
    0.77
     combattre
    0.76
     Fak
    0.75
     Taiwanese
    0.75
    Fak
    0.74
    bew
    0.74
    甃
    0.73
    Hercules
    0.73
     Socks
    0.72
    Activations Density 0.103%

    No Known Activations