© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128352
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on tokens that appear in author bylines, corporate/organization names, and formal citation metadata (e.g. names and citation numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    AEA News Release

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     by
    -1.02
     Kelurahan
    -0.96
     –
    -0.96
    lu
    -0.90
     each
    -0.89
    m
    -0.89
     البلد
    -0.89
    in
    -0.89
    an
    -0.88
    es
    -0.86
    POSITIVE LOGITS
     предлагает
    1.19
    Fakta
    1.10
     ganancia
    1.09
     deliciosos
    1.07
    apkan
    1.03
    readFileSync
    1.02
     píše
    1.01
     lác
    1.00
    Eigenschaften
    0.98
    Kamera
    0.98
    Activations Density 0.035%

    No Known Activations