© 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. 56010
    Prev
    Next
    INDEX
    Explanations

    specific events

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

    The neuron strongly fires on open‐class content words (nouns and verbs) rather than on 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_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
     içerisinde
    -1.42
     tasked
    -1.36
    立马
    -1.31
     онлайн
    -1.28
     aujourd
    -1.24
     trebui
    -1.21
     instrucción
    -1.20
     standalone
    -1.16
     también
    -1.16
    |}{
    -1.15
    POSITIVE LOGITS
     doubtless
    1.35
     scarcely
    1.34
     evidently
    1.27
     merely
    1.23
     dependable
    1.22
     innumerable
    1.16
     adequate
    1.15
     nifty
    1.14
     markedly
    1.13
     even
    1.13
    Activations Density 0.073%

    No Known Activations