© 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. 10-GEMMASCOPE-RES-131K
    7. 20830
    Prev
    Next
    INDEX
    Explanations

    veer Singh

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

    The neuron selectively activates on capitalized tokens that are parts of proper names (people’s names or place names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     tardes
    -2.28
    ﺅ
    -2.23
     \&
    -2.22
     blusas
    -2.08
     bezoek
    -2.06
     \"
    -2.03
    为您
    -2.02
     supermercados
    -2.00
     店内
    -1.98
     sobremesa
    -1.93
    POSITIVE LOGITS
    2
    3.13
    8
    2.91
    7
    2.77
    3
    2.73
    4
    2.73
    9
    2.55
    is
    2.41
    It
    2.25
    These
    2.23
    6
    2.22
    Activations Density 0.007%

    No Known Activations