© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72960
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron activates on numeric literals (standalone numbers, including integers and 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_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
     will
    -1.97
     before
    -1.85
     epitom
    -1.84
     indicating
    -1.83
     coupled
    -1.77
     nearing
    -1.75
     meticulous
    -1.74
     noticeably
    -1.73
     disconcer
    -1.70
     lavish
    -1.66
    POSITIVE LOGITS
     diverses
    2.22
     cinq
    2.08
     overarching
    2.03
     the
    2.03
    ܆
    2.00
     créer
    1.94
    various
    1.88
     télécharger
    1.88
     ridiculously
    1.85
     acheter
    1.84
    Activations Density 0.017%

    No Known Activations