© 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. 34-GEMMASCOPE-RES-131K
    7. 108107
    Prev
    Next
    INDEX
    Explanations

    code and licenses

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

    The neuron detects numeric tokens (digits or 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_34/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
    ्यों
    -0.77
    طان
    -0.74
     Eriksen
    -0.71
     Voltaire
    -0.71
     Wyd
    -0.71
    épa
    -0.70
     reduc
    -0.69
     Vanity
    -0.68
     pairings
    -0.68
     Chees
    -0.68
    POSITIVE LOGITS
     Bor
    0.79
     Smooth
    0.75
     Tam
    0.75
     originated
    0.68
     smoothness
    0.68
     spreading
    0.67
     Sank
    0.67
     schä
    0.66
     locks
    0.65
     Tim
    0.65
    Activations Density 0.031%

    No Known Activations