© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    names of people or places

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

    The main thing this neuron does is detect numeric tokens (numbers).

    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
     and
    -1.08
    되는
    -0.89
    ẩ
    -0.86
     折りたたみ
    -0.85
     населення
    -0.85
    യും
    -0.83
    wanzig
    -0.82
     ditto
    -0.81
     náš
    -0.80
     Ceci
    -0.79
    POSITIVE LOGITS
     it
    1.38
     It
    1.09
     originalmente
    1.03
     who
    0.93
     brukt
    0.92
     servir
    0.92
     originally
    0.91
     Garantie
    0.88
     оно
    0.86
    本來
    0.85
    Activations Density 0.096%

    No Known Activations