© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103774
    Prev
    Next
    INDEX
    Explanations

    brand name or domain name

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

    This neuron detects tokens that function as formal names or labels—e.g. brand names, trade names, code names, and domain identifiers.

    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
     morphism
    -0.76
    ⟵
    -0.75
    حية
    -0.73
    sterne
    -0.71
    wati
    -0.70
     Pieter
    -0.68
    CTION
    -0.68
     Bernie
    -0.68
    кульп
    -0.68
    sioni
    -0.67
    POSITIVE LOGITS
     name
    3.70
    name
    2.95
     names
    2.86
     Name
    2.44
    Name
    2.42
    names
    2.27
    NAME
    2.17
     NAME
    2.06
     Names
    1.95
    名前
    1.95
    Activations Density 0.040%

    No Known Activations