© 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. 10-GEMMASCOPE-RES-131K
    4. 12472
    Prev
    Next
    INDEX
    Explanations

    life and survival

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

    phrases related to fighting for or saving one's life.

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

    The neuron flags words and phrases that evoke life‐or‐death urgency—terms like “life,” “fight,” “survival,” and running for one’s life.

    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
     deuda
    -1.67
     same
    -1.57
    »?
    -1.52
     Gefäng
    -1.46
    一樣
    -1.45
    玙
    -1.45
    '}';
    -1.41
     doméstico
    -1.40
     pureza
    -1.40
     balení
    -1.39
    POSITIVE LOGITS
     from
    1.52
     in
    1.41
    be
    1.20
     Not
    1.16
     були
    1.13
    ak
    1.10
    くると
    1.09
     not
    1.08
     TMPro
    1.08
     sistem
    1.07
    Activations Density 0.011%

    No Known Activations