© 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. 3633
    Prev
    Next
    INDEX
    Explanations

    El Paso

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

    The neuron fires most strongly on isolated single-character tokens—letters, digits, or symbols—rather than on multi-character words.

    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
     how
    -1.91
     nuestros
    -1.85
     nasze
    -1.84
     why
    -1.83
     our
    -1.80
     próximas
    -1.73
    でしたか
    -1.69
     nossa
    -1.67
     nuestras
    -1.66
     calentamiento
    -1.66
    POSITIVE LOGITS
     yng
    1.85
     dakota
    1.70
    做
    1.65
    进入
    1.59
    会
    1.59
    If
    1.58
     juventus
    1.55
     Antwerpen
    1.55
     
    1.52
    ING
    1.51
    Activations Density 0.024%

    No Known Activations