© 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. 20321
    Prev
    Next
    INDEX
    Explanations

    word beginnings and completions

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

    This neuron fires on tokens that contain the letter‐sequence “ap.”

    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
    "
    -2.20
     ferv
    -2.13
     l
    -2.03
    镒
    -2.00
     koruyucu
    -1.96
    沙漠
    -1.95
    in
    -1.91
    preprint
    -1.86
     kaplama
    -1.86
     proven
    -1.85
    POSITIVE LOGITS
    ამ
    3.33
    痈
    2.50
    结语
    2.11
    淠
    2.08
     wadah
    2.05
     Они
    2.03
    ẢN
    2.03
     kekinian
    2.02
     我们
    1.95
    翫
    1.95
    Activations Density 0.000%

    No Known Activations