© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62593
    Prev
    Next
    INDEX
    Explanations

    organizational names and states

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

    The neuron highly activates on long runs of space/tab characters (indentation blocks) in fixed-width or struct-style text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    PDF
    -0.84
    釜
    -0.77
    tapan
    -0.77
    泣
    -0.76
    jButton
    -0.76
    LING
    -0.73
    aringan
    -0.73
     benötigen
    -0.72
    illips
    -0.72
    soni
    -0.71
    POSITIVE LOGITS
     organization
    1.08
     Organizational
    1.05
    Organizational
    1.04
     organisation
    1.02
     Organization
    1.00
     organización
    0.99
    organization
    0.96
     CN
    0.96
     organiza
    0.96
    Organization
    0.95
    Activations Density 0.059%

    No Known Activations