© 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. 22-GEMMASCOPE-RES-131K
    7. 68344
    Prev
    Next
    INDEX
    Explanations

    early career stages

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

    The neuron fires on occurrences of the word “career,” especially in section headings (e.g. “Professional career,” “Club career,” etc.).

    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
    ヂ
    -0.90
    𝑝
    -0.89
    typename
    -0.87
    -0.86
    simple
    -0.85
    -0.82
    是一款
    -0.82
    ท้าย
    -0.82
    -0.82
     لس
    -0.81
    POSITIVE LOGITS
    <h3>
    1.03
     başladı
    1.00
    ưới
    0.90
    以下
    0.89
     below
    0.88
    dziew
    0.88
     comenz
    0.86
     before
    0.85
    orchid
    0.85
    まずは
    0.84
    Activations Density 0.090%

    No Known Activations