© 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. 10-GEMMASCOPE-RES-131K
    7. 105841
    Prev
    Next
    INDEX
    Explanations

    the number two

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

    The neuron fires on occurrences of the standalone word “Two” (often in enumerations or as a numeral component).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     行っ
    -2.20
    5
    -2.17
    A
    -2.17
    $
    -2.11
     SPAIN
    -2.09
    '
    -2.05
    おはよう
    -2.02
    x
    -2.00
    T
    -1.98
    4
    -1.92
    POSITIVE LOGITS
    ſtra
    2.48
    珦
    2.42
     occupé
    2.27
    ization
    2.22
    ological
    2.16
    
    2.09
     WHILE
    2.08
     Former
    2.06
     the
    2.05
     Who
    2.02
    Activations Density 0.029%

    No Known Activations