© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49197
    Prev
    Next
    INDEX
    Explanations

    titles followed by proper nouns

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

    The neuron strongly activates on capitalized proper nouns—especially personal names and title words.

    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
     ihrem
    -0.88
     their
    -0.84
     拖
    -0.83
    ar
    -0.82
     duża
    -0.81
     schreibt
    -0.79
    ｃｍ
    -0.77
     广告
    -0.77
     队
    -0.76
    如下图
    -0.75
    POSITIVE LOGITS
     himself
    1.48
    himself
    1.23
     Mr
    1.02
    بالإ
    1.02
    Mr
    0.98
     telefone
    0.96
    先生
    0.90
    paikan
    0.90
    fitrión
    0.90
     Lainnya
    0.88
    Activations Density 0.039%

    No Known Activations