© 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. 75076
    Prev
    Next
    INDEX
    Explanations

    some [plural noun] [verb]

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

    The neuron activates strongly on adjacent content words forming compound noun phrases that label specific topics or categories (e.g. “social media management tools,” “surgical procedures,” “winter vegetables,” etc.).

    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
     any
    -1.52
     qualsiasi
    -1.29
    任何
    -1.29
    any
    -1.28
     allerlei
    -1.27
     sowieso
    -1.23
     nimmer
    -1.22
     qualunque
    -1.21
    wasn
    -1.21
     любом
    -1.19
    POSITIVE LOGITS
     might
    2.36
     may
    2.28
     некоторых
    1.95
     некоторые
    1.95
     algunos
    1.91
     algunas
    1.91
     niektórych
    1.80
     برخی
    1.70
     Algunos
    1.68
    Algunos
    1.68
    Activations Density 0.084%

    No Known Activations