© 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. 76525
    Prev
    Next
    INDEX
    Explanations

    elder followed by noun

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

    This neuron detects occurrences of the word “Elder,” especially as part of titles or headings.

    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
    ということです
    -0.76
    队长
    -0.75
     Revel
    -0.73
     epithet
    -0.72
     ويمكن
    -0.72
    神経
    -0.72
    igen
    -0.72
     Reduces
    -0.70
    ीन
    -0.68
    ツイート
    -0.68
    POSITIVE LOGITS
    berry
    1.42
     statesman
    1.40
     statesmen
    1.31
    flower
    1.28
    lies
    1.26
     Statesman
    1.15
     Scrolls
    1.13
     abuse
    1.11
    berries
    1.05
    িয়ে
    1.01
    Activations Density 0.011%

    No Known Activations