© 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. 34-GEMMASCOPE-RES-131K
    7. 107299
    Prev
    Next
    INDEX
    Explanations

    being friends

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

    The neuron fires on words and phrases that express positive social bonds or closeness (e.g. “good friends,” “close,” “buddies”).

    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
    Agre
    -0.82
    flan
    -0.81
    рад
    -0.78
    Glej
    -0.75
    eronau
    -0.73
    xically
    -0.71
    这两
    -0.71
     Phal
    -0.70
    removeFrom
    -0.70
    ęs
    -0.70
    POSITIVE LOGITS
     friends
    4.59
    friends
    3.33
     friend
    3.19
     Friends
    2.89
    Friends
    2.88
    friend
    2.83
     friendship
    2.75
     FRIENDS
    2.63
    朋友
    2.55
     Friend
    2.34
    Activations Density 0.029%

    No Known Activations