© 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. 105309
    Prev
    Next
    INDEX
    Explanations

    FYI, folklore

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

    This neuron fires on signpost tokens that introduce supplemental or sectional information—most prominently “FYI” and occurrences of “folklore.”

    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
    锖
    -4.22
    憷
    -3.64
    acea
    -3.08
    mpagne
    -3.06
    摭
    -3.03
    archiwizowane
    -3.03
    eada
    -3.02
    ⎚
    -2.88
    咈
    -2.88
     nahil
    -2.88
    POSITIVE LOGITS
    2
    5.31
    4
    4.19
    1
    4.13
    0
    4.06
    T
    3.81
    U
    3.77
    In
    3.77
    8
    3.75
    6
    3.72
    7
    3.66
    Activations Density 0.005%

    No Known Activations