© 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. 90161
    Prev
    Next
    INDEX
    Explanations

    questions, headings, and starting phrases

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

    The neuron fires on all-caps abbreviations and acronyms (e.g. “RTI2-B,” “RTI,” “JCE,” etc.).

    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
    valores
    -0.77
     standoff
    -0.73
     voorbere
    -0.73
     saveur
    -0.73
     összefoglal
    -0.72
     extérieure
    -0.70
    適
    -0.69
    numericUpDown
    -0.69
     africaine
    -0.69
     stmt
    -0.69
    POSITIVE LOGITS
     intervention
    1.32
     Tier
    1.27
     data
    1.13
     interventions
    1.13
     Intervention
    1.09
    intervention
    1.05
    Intervention
    1.02
     intervene
    1.01
    Tier
    0.98
     tier
    0.97
    Activations Density 0.015%

    No Known Activations