© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106126
    Prev
    Next
    INDEX
    Explanations

    states of being alive

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

    references to "Living" at the beginning of a sentence or phrase.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron consistently lights up on occurrences of the word “living” (or “Living”), especially as a standalone term in titles or headings.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Preco
    -0.86
     Estación
    -0.85
     âges
    -0.85
     Yucatán
    -0.81
     pleins
    -0.81
    kommen
    -0.79
    Trick
    -0.78
     Bahía
    -0.78
     Privy
    -0.77
     Ush
    -0.77
    POSITIVE LOGITS
     living
    1.52
     breathing
    1.40
     Living
    1.14
     legend
    1.06
    living
    1.05
     proof
    0.99
    Living
    0.98
     dead
    0.97
    breathing
    0.92
    LIVING
    0.92
    Activations Density 0.020%

    No Known Activations