© 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. 104476
    Prev
    Next
    INDEX
    Explanations

    advance public health, autonomous vehicles, learners' knowledge

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

    the neuron consistently activates on occurrences of the word “advance” (and its inflected forms like “advancing”).

    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
     }))
    -1.63
    uminense
    -1.61
     erhoben
    -1.58
    towane
    -1.58
     nieuw
    -1.56
     новом
    -1.55
     }],
    -1.53
     necessity
    -1.51
    的风
    -1.51
    Sedangkan
    -1.49
    POSITIVE LOGITS
    ↵
    2.61
    </i>
    2.05
    ’
    1.95
     "
    1.85
    </b>
    1.80
    h
    1.74
    m
    1.58
    </h5>
    1.51
     pelajar
    1.51
    year
    1.48
    Activations Density 0.004%

    No Known Activations