© 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. 39166
    Prev
    Next
    INDEX
    Explanations

    connecting related items

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

    The neuron responds to numeric tokens—i.e. it detects numbers (digits or numeric constants) 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
     encargado
    -0.78
     Ajouter
    -0.77
     Muchas
    -0.77
     Suivez
    -0.73
     Personne
    -0.73
    stoma
    -0.72
     случаи
    -0.70
     který
    -0.70
    Adds
    -0.69
     Outils
    -0.68
    POSITIVE LOGITS
    chukwu
    0.83
    
    0.81
    !*
    0.81
     menemp
    0.77
    rator
    0.77
    cepteur
    0.76
    cyjne
    0.75
    kkkk
    0.74
    ických
    0.74
    endencias
    0.74
    Activations Density 0.057%

    No Known Activations