© 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. 4218
    Prev
    Next
    INDEX
    Explanations

    links to code or numbered items

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

    The neuron strongly fires on title‐ or heading‐style tokens—especially uppercase words, all-caps phrases, numbers, and Markdown/section header markers that appear in section or article titles.

    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
    mont
    -0.73
     aparente
    -0.73
     visto
    -0.69
     made
    -0.69
    mp
    -0.68
    Annex
    -0.68
    ☀️
    -0.68
    のお
    -0.68
    %%
    -0.66
     tận
    -0.66
    POSITIVE LOGITS
     we
    0.92
    我們
    0.90
    我们
    0.90
    gios
    0.89
    PREVIOUS
    0.84
     Resmi
    0.82
     recorte
    0.82
    獪
    0.82
    kuh
    0.81
    setFlags
    0.81
    Activations Density 0.011%

    No Known Activations