© 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. 34729
    Prev
    Next
    INDEX
    Explanations

    determiner 'a' or 'an'

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

    The neuron strongly activates on numeric tokens (digits and numbers, including decimals).

    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
    . 
    -1.01
    Elekt
    -0.96
     ار
    -0.95
    miques
    -0.95
     außerhalb
    -0.94
    ichert
    -0.93
    Frem
    -0.93
    brities
    -0.93
    يكية
    -0.92
    Hva
    -0.91
    POSITIVE LOGITS
     given
    1.45
     these
    1.39
     any
    1.36
     this
    1.32
     such
    1.20
     tersebut
    1.20
    miljø
    1.15
     Lippen
    1.07
    rajz
    1.07
     ANY
    1.05
    Activations Density 0.061%

    No Known Activations