© 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. 107496
    Prev
    Next
    INDEX
    Explanations

    cer or ceres. cer or ceres

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

    names of taxonomic entities, particularly scientific classifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on tokens beginning with the substring “cer” (e.g. Cer- brands, Ceriodaphnia, Certify, etc.).

    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
    endiendo
    -0.82
     ч
    -0.80
    ⋇
    -0.77
    ünsche
    -0.77
     breeze
    -0.77
    éfonos
    -0.75
     канал
    -0.74
     лука
    -0.73
    cepteur
    -0.73
    jście
    -0.73
    POSITIVE LOGITS
     Cer
    0.84
     Ibid
    0.83
    Issued
    0.78
     Jl
    0.78
    VIEWS
    0.77
    Cer
    0.76
    cer
    0.76
     CER
    0.75
     Ceres
    0.74
     цену
    0.73
    Activations Density 0.045%

    No Known Activations