© 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. 22-GEMMASCOPE-RES-131K
    4. 27974
    Prev
    Next
    INDEX
    Explanations

    both ... and .

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

    The neuron fires on open‐class content words (nouns and adjectives) rather than on function or stop 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
     in
    -1.78
     other
    -1.54
     (
    -1.30
     will
    -1.29
     I
    -1.24
     to
    -1.20
    a
    -1.18
    in
    -1.13
    da
    -1.13
     on
    -1.12
    POSITIVE LOGITS
     and
    2.81
     zowel
    1.95
     både
    1.63
     or
    1.63
     וגם
    1.55
     verschill
    1.54
     maupun
    1.53
     yayınları
    1.38
     sağlar
    1.33
     sowohl
    1.30
    Activations Density 0.073%

    No Known Activations