© 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. 75163
    Prev
    Next
    INDEX
    Explanations

    specific nouns after determiners

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

    This neuron detects boilerplate or meta‐text passages—user‐facing site notices, subscription or cookie disclaimers, “for this article/our website/you …,” license statements, and similar administrative copy.

    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
     its
    -1.52
     their
    -1.18
     they
    -1.13
     by
    -1.10
     it
    -1.08
     and
    -1.06
     tertawa
    -1.02
     evidence
    -1.02
    tidos
    -1.01
    Olvid
    -1.01
    POSITIVE LOGITS
     insom
    1.10
     inco
    1.02
    ()=>{
    1.02
     нее
    1.00
     geos
    0.98
    וך
    0.97
     diabo
    0.97
    camento
    0.97
    islav
    0.97
     enigma
    0.94
    Activations Density 0.117%

    No Known Activations