© 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. 34-GEMMASCOPE-RES-131K
    4. 102782
    Prev
    Next
    INDEX
    Explanations

    chemical elements and metals

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

    lists of chemical elements and metals.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to numeric measurement values—especially concentrations or quantities (often of chemical elements or metals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⋇
    -0.90
    кет
    -0.89
    できます
    -0.88
    エア
    -0.85
    |_{\
    -0.85
    MatInputModule
    -0.85
     Grunds
    -0.84
    перь
    -0.84
    Ferien
    -0.82
     أمريكي
    -0.80
    POSITIVE LOGITS
     zinc
    1.39
     copper
    1.34
     lead
    1.16
     manganese
    1.13
     iron
    1.09
     stron
    1.05
    lead
    1.02
     aluminum
    1.01
    copper
    0.98
     calcium
    0.97
    Activations Density 0.058%

    No Known Activations