© 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. 55601
    Prev
    Next
    INDEX
    Explanations

    academic work, research, projects

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

    The neuron fires on nouns referring to scholarly work and research activities (e.g. “project,” “work,” “research,” “paper,” “discussion,” “genetic”).

    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
     rospy
    -0.77
    /.../
    -0.77
    Hear
    -0.73
    copies
    -0.73
    emas
    -0.72
    BBB
    -0.71
    jira
    -0.71
    ICY
    -0.70
    mop
    -0.70
     COMES
    -0.69
    POSITIVE LOGITS
     radi
    0.64
    вото
    0.62
    frontmatter
    0.62
    owskiego
    0.61
     Direct
    0.61
    bygg
    0.60
     Macau
    0.60
    ३
    0.60
     Strong
    0.60
     nucleic
    0.59
    Activations Density 0.081%

    No Known Activations