© 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. 22-GEMMASCOPE-RES-131K
    7. 67290
    Prev
    Next
    INDEX
    Explanations

    American designs and Jacob names

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

    The neuron is firing on numeric tokens (digits and numbers, including decimals).

    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
     somos
    -1.22
    Pengertian
    -1.20
     bolí
    -1.19
     caract
    -1.13
     mikina
    -1.07
     annon
    -1.06
     TRABAJO
    -1.05
     negros
    -1.03
     nadar
    -1.03
     fré
    -1.02
    POSITIVE LOGITS
    <blockquote>
    1.01
     mehrerer
    1.00
     offenbar
    0.96
    IGENCE
    0.96
     .
    0.96
     zwanzig
    0.95
     diesmal
    0.93
     Al
    0.92
     American
    0.92
     zweier
    0.91
    Activations Density 0.024%

    No Known Activations