© 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. 29988
    Prev
    Next
    INDEX
    Explanations

    scientific instruments and workflows

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

    This neuron strongly activates on multiword capitalized organization or company names (i.e. brand/institution names).

    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
     Schwim
    -0.81
     toallas
    -0.78
     contemporánea
    -0.71
     Mischung
    -0.69
    激活
    -0.69
     británica
    -0.69
    了一会儿
    -0.69
     分页
    -0.68
     refusal
    -0.68
     motivadoras
    -0.68
    POSITIVE LOGITS
     instruments
    1.46
     instrument
    1.36
     workflows
    1.31
    instrument
    1.26
     workflow
    1.24
    Instrument
    1.24
     Instruments
    1.23
     consumables
    1.20
     Workflow
    1.20
     Instrument
    1.17
    Activations Density 0.056%

    No Known Activations