© 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. 10-GEMMASCOPE-RES-131K
    4. 102069
    Prev
    Next
    INDEX
    Explanations

    words ending in -ancy and -ity

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

    The neuron lights up on longer, content‐bearing words (mostly nouns and adjectives) rather than 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_10/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
    (
    -2.05
    -2.00
     by
    -1.94
     then
    -1.84
     each
    -1.79
     both
    -1.76
     those
    -1.74
     their
    -1.66
    b
    -1.63
    v
    -1.60
    POSITIVE LOGITS
    曖昧さ
    1.83
     zei
    1.75
     sözler
    1.56
     berge
    1.49
    CONCEPT
    1.48
     bukanlah
    1.47
     elegante
    1.47
    bied
    1.46
     strategia
    1.44
    Ѵ
    1.44
    Activations Density 0.110%

    No Known Activations