© 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. 34-GEMMASCOPE-RES-131K
    4. 87025
    Prev
    Next
    INDEX
    Explanations

    IT system names or comments

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

    The neuron fires on numeric tokens (numbers and digit‐based sequences).

    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
    SNA
    -0.78
    ǿ
    -0.76
    叽
    -0.75
    Lina
    -0.73
    ムラ
    -0.71
     Femme
    -0.70
    quran
    -0.70
     Sei
    -0.69
     smokers
    -0.69
    otry
    -0.69
    POSITIVE LOGITS
     ITS
    1.38
     incident
    1.15
     Incident
    1.14
    incident
    1.09
     Service
    1.06
     Remedy
    1.06
     service
    1.05
    IT
    1.02
     BMC
    0.99
    Service
    0.96
    Activations Density 0.023%

    No Known Activations