© 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. 87075
    Prev
    Next
    INDEX
    Explanations

    Chief administrative officer

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

    The neuron fires on long numeric tokens (multi-digit numbers, e.g. years or large numeric codes).

    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
     الوطنيه
    -0.75
    hébergement
    -0.75
    Hemos
    -0.71
     ترك
    -0.70
    рое
    -0.69
    impianto
    -0.69
    entuh
    -0.69
     TextEditing
    -0.68
    perus
    -0.68
     Mentre
    -0.67
    POSITIVE LOGITS
     astrology
    1.20
     Advanced
    1.20
     Alemania
    1.19
     Azure
    1.16
     Armor
    1.16
    Autowired
    1.15
     Arbeits
    1.15
     arrogance
    1.14
     Arctic
    1.12
     aerospace
    1.12
    Activations Density 0.105%

    No Known Activations