© 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. 66206
    Prev
    Next
    INDEX
    Explanations

    technical setup and procedures

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

    This neuron identifies the main action verb (e.g. use, store, display, carry, create) in a question’s title.

    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
     Eğ
    -0.96
     obligator
    -0.95
     fábrica
    -0.91
     Peña
    -0.87
     creemos
    -0.85
     >>
    -0.85
     novelas
    -0.85
    getdata
    -0.84
     !!
    -0.83
    xxxxxxxxxxxxxxxx
    -0.83
    POSITIVE LOGITS
     career
    0.95
     Careers
    0.88
     procedures
    0.88
     principles
    0.88
     selected
    0.85
     practices
    0.85
     planned
    0.83
     careers
    0.83
     recommended
    0.80
     techniques
    0.80
    Activations Density 0.037%

    No Known Activations