© 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. 34-GEMMASCOPE-RES-131K
    7. 57641
    Prev
    Next
    INDEX
    Explanations

    citations with years

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

    The neuron is selectively activated by standalone numeric tokens (e.g. years, volume/page numbers, citation indexes).

    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
     both
    -2.00
     what
    -1.95
     this
    -1.84
     all
    -1.78
     in
    -1.55
     which
    -1.48
     as
    -1.48
     ALL
    -1.47
     at
    -1.47
     those
    -1.45
    POSITIVE LOGITS
     participer
    1.53
     diriger
    1.45
    Programma
    1.42
    BENEF
    1.37
    Thema
    1.35
    キーボード
    1.34
    不断的
    1.34
    Recept
    1.33
     accompagner
    1.33
     certamente
    1.33
    Activations Density 0.014%

    No Known Activations