© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73609
    Prev
    Next
    INDEX
    Explanations

    old + descriptive word

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

    The main thing this neuron does is detect the word “old.”

    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
    .
    -1.97
     "
    -1.95
     meestal
    -1.73
    鍆
    -1.73
     arou
    -1.66
    鹟
    -1.65
    をチェック
    -1.63
     governs
    -1.61
     essen
    -1.59
    鱨
    -1.58
    POSITIVE LOGITS
     fashioned
    3.11
    、
    2.63
     adage
    2.02
    fashioned
    2.02
    。
    1.99
    j
    1.93
     швидко
    1.92
    或
    1.89
    na
    1.88
     old
    1.88
    Activations Density 0.038%

    No Known Activations