© 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. 10-GEMMASCOPE-RES-131K
    7. 39323
    Prev
    Next
    INDEX
    Explanations

    life or lifetime followed by a noun

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

    phrases related to life sentences, imprisonment, and lifetime periods.

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

    The neuron activates on occurrences of “life” or its derivations (e.g. life, lifetime, lifers) 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_10/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
    泚
    -1.25
    OCD
    -1.18
    HOURS
    -1.18
    鷥
    -1.17
     thuy
    -1.16
    dY
    -1.16
    onViewCreated
    -1.16
    FTS
    -1.16
    genetics
    -1.14
     nhat
    -1.13
    POSITIVE LOGITS
    の人生
    1.27
     devotion
    1.19
    Probl
    1.17
    h
    1.16
    Different
    1.13
     irgende
    1.12
     různých
    1.11
    Among
    1.11
     bądź
    1.10
     lifetime
    1.09
    Activations Density 0.082%

    No Known Activations