© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13486
    Prev
    Next
    INDEX
    Explanations

    nitrogen and its compounds

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

    The neuron recognizes the chemical element nitrogen and its chemical notation (N2).

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

    The neuron is triggered by any mention of “nitrogen” (including its chemical symbols or derivatives).

    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
    M
    -3.56
    P
    -2.73
    تیجه
    -2.70
    on
    -2.66
    T
    -2.56
     ktorí
    -2.42
    K
    -2.42
    O
    -2.38
    I
    -2.36
    R
    -2.36
    POSITIVE LOGITS
    .
    3.42
     '
    2.47
    ization
    2.39
    蠓
    2.33
    姈
    2.28
    媗
    2.22
    蟜
    2.17
    迓
    2.08
     rękaw
    2.06
    蘼
    2.06
    Activations Density 0.005%

    No Known Activations