© 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. 10-GEMMASCOPE-RES-131K
    7. 60238
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific nouns

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

    The neuron detects numeric tokens (number literals, including those with decimals) 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_10/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
    jzen
    -1.93
    ztes
    -1.92
     doInBackground
    -1.91
    fordshire
    -1.88
    tician
    -1.86
    BURGH
    -1.84
    
    -1.81
     estructura
    -1.78
    Formik
    -1.74
     ieder
    -1.73
    POSITIVE LOGITS
     from
    2.58
     one
    2.44
     two
    2.38
     with
    2.27
     Each
    2.19
    Not
    2.02
     From
    1.95
     setelah
    1.95
     three
    1.94
     first
    1.93
    Activations Density 0.008%

    No Known Activations