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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90787
    Prev
    Next
    INDEX
    Explanations

    since + verb or pronoun

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

    The neuron fires on the first‐person plural pronoun “we” (including forms like “we’re” or “we’ve”).

    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
     should
    -1.63
     when
    -1.52
     however
    -1.45
     even
    -1.45
     either
    -1.36
     entweder
    -1.30
     which
    -1.30
     if
    -1.26
     because
    -1.25
     потому
    -1.20
    POSITIVE LOGITS
     already
    2.11
    如此
    1.66
     столь
    1.63
     ormai
    1.53
    already
    1.48
     only
    1.33
    这么多
    1.31
     zaten
    1.30
     endast
    1.29
    Already
    1.28
    Activations Density 0.077%

    No Known Activations