© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129479
    Prev
    Next
    INDEX
    Explanations

    This neuron is triggered by numeric literals (numbers) in code or markup.

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

    UI code and scientific terms

    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
     Unterneh
    -1.30
     Beobachtungen
    -1.27
     Empfang
    -1.21
     Könige
    -1.19
    atán
    -1.17
     INFORMACIÓN
    -1.16
     Ansprechpartner
    -1.16
     Betrach
    -1.14
     Veränderungen
    -1.14
     Início
    -1.13
    POSITIVE LOGITS
    e
    1.23
    n
    1.18
    これも
    1.09
    D
    1.07
    E
    1.05
    De
    1.02
    S
    1.02
    M
    1.01
     bukanlah
    1.00
    k
    0.98
    Activations Density 0.001%

    No Known Activations