© 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. 99839
    Prev
    Next
    INDEX
    Explanations

    names

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

    This neuron detects personal proper names (people’s first or last names) in the text.

    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
     gepub
    -1.38
     and
    -0.96
     without
    -0.96
     pères
    -0.93
    ใคร
    -0.93
    ไหน
    -0.93
     behoort
    -0.91
    énom
    -0.91
    》(
    -0.90
     same
    -0.89
    POSITIVE LOGITS
    viii
    1.08
    ↵↵↵
    1.04
     vitales
    1.02
    vii
    1.01
     kanske
    0.98
     櫻
    0.98
     deixa
    0.98
     vinaigre
    0.98
     betyd
    0.97
     föres
    0.97
    Activations Density 0.039%

    No Known Activations