© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91309
    Prev
    Next
    INDEX
    Explanations

    header files or first elements

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

    The neuron is essentially triggered by any occurrence of the token “head” (in any casing or context).

    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
     pret
    -0.88
     guise
    -0.76
    "%
    -0.76
     pretense
    -0.72
     protein
    -0.70
    пуска
    -0.68
     Cote
    -0.67
     Blanc
    -0.67
     Colonel
    -0.66
     postępo
    -0.66
    POSITIVE LOGITS
     tiên
    0.94
    Ứ
    0.81
    dü
    0.79
     véritables
    0.79
    ас
    0.79
    کرد
    0.76
    FileUtils
    0.75
    屿
    0.74
     размер
    0.73
     exo
    0.73
    Activations Density 0.015%

    No Known Activations