© 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. 668
    Prev
    Next
    INDEX
    Explanations

    mystery and enigma

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

    The neuron selectively activates on numeric tokens (multi-digit numbers).

    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
    щита
    -0.84
    inev
    -0.83
    extré
    -0.80
    upc
    -0.80
     выбирать
    -0.80
    ベルト
    -0.78
    illés
    -0.76
    ρι
    -0.75
    jaguar
    -0.75
     취
    -0.74
    POSITIVE LOGITS
     mystery
    5.81
     mysteries
    4.78
    mystery
    4.44
    Mystery
    4.06
     Mystery
    4.06
     mysterious
    3.81
     enigma
    3.27
    謎
    3.19
     Mysteries
    3.17
     mystère
    3.00
    Activations Density 0.101%

    No Known Activations