© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73880
    Prev
    Next
    INDEX
    Explanations

    how do you or i

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

    The neuron fires on question‐forming function words (e.g. “How,” “do,” “Can,” “Did,” etc.), i.e. it detects interrogative openings.

    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
     that
    -1.17
     do
    -1.08
     möglicherweise
    -1.01
     場所
    -0.94
     it
    -0.93
     น่า
    -0.91
     Fälle
    -0.90
     eftersom
    -0.90
     coopération
    -0.86
    簡単な
    -0.86
    POSITIVE LOGITS
     you
    2.34
     we
    1.69
     I
    1.63
     i
    1.54
     You
    1.16
     anyone
    1.09
     можно
    1.07
     children
    1.02
     мы
    1.02
     я
    1.01
    Activations Density 0.061%

    No Known Activations