© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13225
    Prev
    Next
    INDEX
    Explanations

    HTML structure tags

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

    The neuron strongly activates on numeric tokens (digits or numbers) wherever they appear in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    导师
    -0.81
     دیدار
    -0.78
    utzer
    -0.78
    
    -0.75
     adenocarcinoma
    -0.75
    isław
    -0.75
     Гар
    -0.74
    żna
    -0.73
     couverte
    -0.73
     rigs
    -0.73
    POSITIVE LOGITS
     further
    1.11
     httpClient
    0.93
    ̞
    0.88
    juin
    0.86
     kasama
    0.84
    urther
    0.83
     mexico
    0.82
     itself
    0.81
     others
    0.81
     FileSystem
    0.81
    Activations Density 0.043%

    No Known Activations