© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48135
    Prev
    Next
    INDEX
    Explanations

    data reporting and submission

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

    The neuron is specialized to detect numeric expressions (multi‐digit figures and statistics) 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
    nasio
    -0.84
    searchText
    -0.80
     υπάρχ
    -0.79
    árd
    -0.78
     conforto
    -0.76
    توض
    -0.73
    Races
    -0.73
    rscheinlichkeit
    -0.73
     considerazione
    -0.73
     discussions
    -0.73
    POSITIVE LOGITS
     reporting
    3.02
    reporting
    2.39
     Reporting
    2.36
    Reporting
    2.28
     submission
    2.20
     report
    2.17
     REPORTING
    2.09
     submit
    1.96
     reports
    1.96
     submitted
    1.94
    Activations Density 0.024%

    No Known Activations