© 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. 34-GEMMASCOPE-RES-131K
    7. 337
    Prev
    Next
    INDEX
    Explanations

    html/template/code punctuation

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

    The neuron is selectively activated by numeric tokens (literal numbers or digits) 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_34/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
     Orr
    -0.71
    キャスト
    -0.70
    ade
    -0.69
    jutant
    -0.68
    Somewhere
    -0.68
     Communicate
    -0.68
     সে
    -0.65
     топли
    -0.65
    xian
    -0.65
    {/*
    -0.65
    POSITIVE LOGITS
    eaus
    0.74
    }^{(\
    0.72
    perl
    0.72
    нару
    0.71
    kata
    0.66
     mutiara
    0.65
    yac
    0.65
    pueblo
    0.65
     lieber
    0.65
     Kredit
    0.64
    Activations Density 0.058%

    No Known Activations