© 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. 22-GEMMASCOPE-RES-131K
    7. 28409
    Prev
    Next
    INDEX
    Explanations

    purpose or specific context

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

    The neuron strongly activates on terms that denote experimental methods, measurements, or research‐design elements in scientific texts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    felizmente
    -1.16
     initComponents
    -1.13
    beit
    -1.07
    などが
    -1.05
    なども
    -1.04
     Struggle
    -1.03
    nemies
    -1.02
     Ꮎ
    -1.02
     možnosti
    -1.01
    tilen
    -1.00
    POSITIVE LOGITS
     circumstances
    1.52
     intended
    1.46
     specific
    1.44
     needs
    1.41
     particular
    1.40
     required
    1.38
     purpose
    1.32
     purposes
    1.30
     situations
    1.26
     each
    1.23
    Activations Density 0.067%

    No Known Activations