© 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. 22-GEMMASCOPE-RES-131K
    7. 13674
    Prev
    Next
    INDEX
    Explanations

    why, what, how

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

    The neuron tends to fire on content‐bearing words (nouns, adjectives, and other semantically significant terms) rather than on common function words.

    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
     the
    -1.36
     these
    -1.33
     wali
    -1.20
     nuove
    -1.20
     taal
    -1.09
     piante
    -1.06
    ṉ
    -1.05
     [{
    -1.05
     vitamine
    -1.05
     bata
    -1.05
    POSITIVE LOGITS
     then
    2.66
     why
    2.09
     Then
    1.95
     Why
    1.87
     How
    1.68
     how
    1.66
     what
    1.59
     What
    1.52
     entonces
    1.48
     that
    1.44
    Activations Density 0.024%

    No Known Activations