© 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. 83676
    Prev
    Next
    INDEX
    Explanations

    descriptions of buildings and locations

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

    The neuron is picking up on section headings or title–style spans (blocks of largely uppercase or capitalized words often preceded by line breaks and extra whitespace).

    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
     our
    -1.29
     new
    -1.21
     their
    -1.08
    ษัท
    -1.05
     neuen
    -1.00
    নের
    -1.00
     pojawi
    -0.95
     daarbij
    -0.95
     கே
    -0.95
     Turnier
    -0.94
    POSITIVE LOGITS
     worth
    1.37
    konstruktion
    1.13
    ichtigung
    1.13
     worthwhile
    1.09
    もし
    1.05
     is
    1.02
     interessant
    1.01
    您可以
    1.00
    Історія
    1.00
     tourists
    1.00
    Activations Density 0.054%

    No Known Activations