© 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. 99092
    Prev
    Next
    INDEX
    Explanations

    indefinite articles

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

    The neuron strongly activates on numeric tokens (i.e. numbers) 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
     těch
    -1.09
     gefüllt
    -1.07
     neumáticos
    -1.05
     tiegħ
    -1.04
     importación
    -1.03
     frenos
    -1.03
     aluminio
    -1.02
     agujeros
    -1.00
    Anonym
    -0.99
     ngunit
    -0.99
    POSITIVE LOGITS
     an
    6.19
    An
    1.63
    an
    1.62
     הא
    1.50
     An
    1.48
     sebuah
    1.40
     dell
    1.38
    了一个
    1.15
     einem
    1.11
     एक
    1.08
    Activations Density 0.460%

    No Known Activations