© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3157
    Prev
    Next
    INDEX
    Explanations

    research studies and specific fields

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

    The neuron activates on capitalized words that are part of formal organization or agency names.

    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
     различи
    -1.08
     anun
    -1.05
     mision
    -1.01
     stili
    -0.96
     Surve
    -0.96
     krem
    -0.96
     concha
    -0.96
     Melayu
    -0.94
     pecuni
    -0.93
     DEPTH
    -0.92
    POSITIVE LOGITS
     Research
    1.10
     Council
    0.93
    Trials
    0.90
     ailing
    0.89
    ↵↵↵
    0.87
     Certain
    0.85
     Хар
    0.84
     ко
    0.83
     anzu
    0.81
     Studies
    0.80
    Activations Density 0.183%

    No Known Activations