© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71958
    Prev
    Next
    INDEX
    Explanations

    on the brink of

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

    The neuron specializes in spotting words that describe being on an edge, boundary, or threshold (e.g., brink, cusp, outskirts, forefront).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     acoged
    -1.69
    ありますか
    -1.52
    偌
    -1.52
     делает
    -1.46
    充滿
    -1.45
     and
    -1.45
     男生
    -1.44
     Zusammensetzung
    -1.42
     regalías
    -1.41
    ㄍ
    -1.41
    POSITIVE LOGITS
     of
    7.31
    ของ
    1.73
     praktis
    1.69
     menyenangkan
    1.64
     retten
    1.63
    沨
    1.63
     kommunik
    1.62
     charmant
    1.59
    ешь
    1.55
     hangat
    1.55
    Activations Density 0.028%

    No Known Activations