© 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. 10-GEMMASCOPE-RES-131K
    7. 24022
    Prev
    Next
    INDEX
    Explanations

    adjective followed by noun

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

    The neuron fires on descriptive modifiers—especially adjectives and adverbs that qualify or intensify nouns (e.g. low, broad, crippling, effective, molecular).

    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
    “
    -1.72
    这些
    -1.48
    3
    -1.47
    。
    -1.47
    }
    -1.46
     oraz
    -1.38
    2
    -1.37
    ↵
    -1.36
    ”
    -1.35
    "
    -1.32
    POSITIVE LOGITS
     that
    1.59
    のかもしれません
    1.56
     who
    1.42
     céu
    1.38
    ͓
    1.34
    殡
    1.34
     Při
    1.32
    ༷
    1.32
    engeti
    1.32
     amortecedor
    1.27
    Activations Density 0.316%

    No Known Activations