© 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. 34-GEMMASCOPE-RES-131K
    7. 103825
    Prev
    Next
    INDEX
    Explanations

    start of document sections

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

    The neuron detects document-structure formatting markers (e.g. list bullets, section headers, and similar punctuation used in metadata or markup).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     краще
    -0.83
    anity
    -0.79
    Aud
    -0.77
    throwaway
    -0.76
    =[[
    -0.75
    _",
    -0.74
     affari
    -0.73
    ClientId
    -0.72
     novidades
    -0.72
     uye
    -0.71
    POSITIVE LOGITS
     inherit
    0.82
    继承
    0.79
     Wizard
    0.78
    inherit
    0.77
    車両
    0.77
     mecánica
    0.72
     Picking
    0.71
     ہیں
    0.70
     Terrorism
    0.70
    idere
    0.70
    Activations Density 0.017%

    No Known Activations