© 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. 22-GEMMASCOPE-RES-131K
    7. 67574
    Prev
    Next
    INDEX
    Explanations

    tree structure

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

    The neuron activates whenever it sees the standalone token “tree.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵
    -3.61
    椟
    -2.66
    檍
    -2.39
    ︐
    -2.33
    silien
    -2.27
     et
    -2.22
    ă
    -2.17
    苤
    -2.17
     genaue
    -2.17
    都在
    -2.17
    POSITIVE LOGITS
    you
    2.69
     gyerek
    2.45
    this
    2.39
     samti
    2.31
    ープン
    2.31
     másik
    2.30
     Their
    2.20
     gyermek
    2.20
    𓆜
    2.19
    </h3>
    2.17
    Activations Density 0.018%

    No Known Activations