© 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. 10-GEMMASCOPE-RES-131K
    7. 60947
    Prev
    Next
    INDEX
    Explanations

    (A) and (B) list items

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

    The neuron is detecting document outline markers or legal/technical section labels (e.g. “(A)”, “(B)”, numbered or lettered clause 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_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
     kalori
    -2.02
    '
    -1.96
    ۔
    -1.79
     bunda
    -1.77
    ?"
    -1.71
     kriminal
    -1.68
     optik
    -1.64
     protokol
    -1.63
     gelas
    -1.62
    。
    -1.60
    POSITIVE LOGITS
     {
    1.48
    忏
    1.42
     flung
    1.40
     直接
    1.40
     neuer
    1.39
     marshall
    1.38
    modèle
    1.37
     People
    1.36
     ston
    1.31
     The
    1.29
    Activations Density 0.025%

    No Known Activations