© 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. 55759
    Prev
    Next
    INDEX
    Explanations

    belong to

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

    The neuron strongly activates on words expressing belonging or association (e.g., “belong,” “belongs,” “belonging”).

    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
    จาก
    -0.98
    一般的
    -0.98
    Tempat
    -0.95
    Bahasa
    -0.94
    による
    -0.92
     going
    -0.91
    瞌
    -0.90
     philanthropic
    -0.90
    änemark
    -0.90
     prefent
    -0.89
    POSITIVE LOGITS
     belongs
    1.69
     pertenec
    1.56
     belonged
    1.50
     belong
    1.48
     Belong
    1.36
     принадле
    1.34
    belong
    1.34
     pertenece
    1.26
     belonging
    1.23
     to
    1.20
    Activations Density 0.034%

    No Known Activations