© 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. 81543
    Prev
    Next
    INDEX
    Explanations

    calling or referring

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

    The neuron is selectively activating on capitalized words and named entities (proper nouns and titles).

    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
    OPIN
    -0.76
     guideline
    -0.75
     Lindberg
    -0.74
     ulasan
    -0.74
     サム
    -0.73
    上がった
    -0.73
    dio
    -0.72
     trùng
    -0.71
    ávají
    -0.71
     icono
    -0.70
    POSITIVE LOGITS
     calling
    2.94
     call
    2.52
     calls
    2.41
     Calling
    2.16
     referred
    2.16
     called
    2.14
     referring
    2.11
    Calling
    2.11
    calling
    2.08
    稱
    2.03
    Activations Density 0.029%

    No Known Activations