© 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. 8401
    Prev
    Next
    INDEX
    Explanations

    buddy and companions

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

    The main thing this neuron does is detect occurrences of the word “buddy.”

    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
    </em>
    -2.48
     in
    -2.41
     její
    -2.23
     často
    -2.23
    𓐍
    -2.19
     französische
    -2.19
     weshalb
    -2.17
    鈊
    -2.17
    猛地
    -2.13
     vollständige
    -2.09
    POSITIVE LOGITS
     Like
    2.52
    地在
    2.33
     fédé
    2.28
     Especially
    2.25
     Ignoring
    2.22
    \
    2.20
     khususnya
    2.20
    Whenever
    2.17
    ########.
    2.17
    Depending
    2.16
    Activations Density 0.005%

    No Known Activations