© 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. 129831
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to numeric expressions and quantity-related tokens (digits, number words, and numerical quantifiers).

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

    phrases like or similar to

    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
    ที่ยว
    -0.92
     otros
    -0.86
     /\.
    -0.85
    خته
    -0.85
    slika
    -0.85
     bairro
    -0.85
    roscopy
    -0.85
    myapp
    -0.82
     dini
    -0.81
     viera
    -0.81
    POSITIVE LOGITS
     similar
    3.89
    similar
    3.39
    Similar
    3.28
     podob
    3.17
     Similar
    3.08
    เหมือน
    2.77
     ähnlich
    2.73
     similarities
    2.72
     like
    2.69
     مشابه
    2.67
    Activations Density 0.177%

    No Known Activations