© 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. 22-GEMMASCOPE-RES-131K
    7. 39101
    Prev
    Next
    INDEX
    Explanations

    we all / we

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

    The neuron is primarily detecting first-person plural pronouns and inclusive “we/our” group-referencing language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     mempertahankan
    -1.18
    いえば
    -1.12
     melahirkan
    -1.09
     if
    -1.08
     oiseau
    -1.02
     even
    -1.02
    лично
    -1.01
    انجليز
    -1.01
     berpeng
    -1.00
     дальнейшем
    -0.98
    POSITIVE LOGITS
     někter
    1.41
     parfois
    1.41
     sometimes
    1.38
     bazı
    1.30
     algunos
    1.25
     kadang
    1.24
     иногда
    1.23
     souvent
    1.23
     algunas
    1.20
     برخی
    1.20
    Activations Density 0.011%

    No Known Activations