© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73239
    Prev
    Next
    INDEX
    Explanations

    start code or section

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

    The neuron strongly activates on the standalone token “Begin.”

    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
    </strong>
    -2.31
    และ
    -2.23
     “
    -2.22
    </u>
    -2.17
    ":
    -2.08
     
    -2.08
     überprü
    -2.05
    .
    -2.03
    奩
    -2.02
    と
    -1.99
    POSITIVE LOGITS
    鄚
    3.00
    寕
    2.28
    Begin
    2.20
    n
    2.09
    蕯
    2.09
    晅
    2.06
     internazionale
    2.06
    kemeja
    2.05
    鏵
    2.02
     terwijl
    2.00
    Activations Density 0.003%

    No Known Activations