© 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. 66591
    Prev
    Next
    INDEX
    Explanations

    career and its main parts

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

    This neuron activates on tokens that mark section headers or titles (e.g. “[Service]” blocks, HTML view classes for page body, markdown “Methods and results,” front-matter “main matter,” etc.). In other words, it detects section-heading labels.

    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
    َن
    -0.87
    וּ
    -0.85
    Ergebnisse
    -0.85
    Dichloropropene
    -0.79
    sihkan
    -0.79
    gü
    -0.78
     lesz
    -0.77
    }}(\
    -0.77
    gume
    -0.77
    sierra
    -0.77
    POSITIVE LOGITS
    地區
    0.93
    obis
    0.90
    itudinal
    0.88
     &&
    0.86
     followed
    0.82
    mismo
    0.81
    followed
    0.81
    llo
    0.80
    HasBeenSet
    0.79
    ONAUT
    0.79
    Activations Density 0.013%

    No Known Activations