© 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. 33370
    Prev
    Next
    INDEX
    Explanations

    words starting with dre

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

    The neuron activates on tokens containing the substring “dre” (especially at the start of proper names or terms).

    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
    orenje
    -0.79
     feel
    -0.77
     monumental
    -0.73
    適当
    -0.73
    箓
    -0.72
    =="")
    -0.71
     away
    -0.71
    焕
    -0.70
    żesz
    -0.69
    剧照
    -0.69
    POSITIVE LOGITS
     dre
    0.98
    PRESENT
    0.85
    getForm
    0.83
    mère
    0.82
     Dre
    0.82
    jacency
    0.81
    Dre
    0.78
     Profile
    0.77
    Profiles
    0.74
    Profile
    0.72
    Activations Density 0.015%

    No Known Activations