© 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. 21800
    Prev
    Next
    INDEX
    Explanations

    sand, sandy soil

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

    The neuron detects mentions of granular particulate materials (e.g., sand, grit, granular particles, clay).

    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
    ’
    -1.67
     similar
    -1.56
    </sup>
    -1.49
     them
    -1.49
     fronteras
    -1.48
    d
    -1.47
     anhänger
    -1.44
     different
    -1.42
    ’，
    -1.41
    EN
    -1.39
    POSITIVE LOGITS
     THAN
    1.66
     потому
    1.58
    าสตร์
    1.56
    ȇ
    1.56
    あります
    1.55
    妧
    1.54
    諍
    1.52
    儚
    1.48
     estaremos
    1.47
     harrowing
    1.45
    Activations Density 0.008%

    No Known Activations