© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84837
    Prev
    Next
    INDEX
    Explanations

    oxides of elements

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

    chemical compounds containing oxygen, particularly metal oxides.

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

    The neuron strongly activates on chemical compound names containing “oxide” or “hydroxide” (e.g., oxides, dioxides, hydroxides).

    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
    for
    -1.77
    e
    -1.64
    ala
    -1.58
    ā
    -1.48
    J
    -1.46
     was
    -1.45
    Z
    -1.45
    SS
    -1.44
    ND
    -1.42
    IA
    -1.42
    POSITIVE LOGITS
     of
    2.02
     Перейти
    1.92
    ğın
    1.81
     possibility
    1.66
    尴
    1.59
     crappy
    1.59
    ꒥
    1.55
    Décès
    1.53
    
    1.50
     verschiedenen
    1.49
    Activations Density 0.042%

    No Known Activations