© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 56085
    Prev
    Next
    INDEX
    Explanations

    isThefivemorningafternoonevening

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

    This neuron fires on tokens that appear in section headings or titles—especially title‐case words and numerals (e.g. “Life,” “:,” “Children,” years, list numbers, etc.).

    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
    λλά
    -0.81
    ījum
    -0.81
    Цель
    -0.79
    Ahhhh
    -0.79
     erupted
    -0.78
     Nair
    -0.78
    ↧
    -0.78
    yaratan
    -0.77
     instagram
    -0.77
     severance
    -0.77
    POSITIVE LOGITS
    weighed
    0.86
    Details
    0.84
     dél
    0.79
     inéd
    0.78
     äl
    0.77
     likened
    0.77
     kys
    0.77
    笑话
    0.76
     visite
    0.75
    ########.
    0.74
    Activations Density 0.001%

    No Known Activations