© 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. 22-GEMMASCOPE-RES-131K
    7. 73040
    Prev
    Next
    INDEX
    Explanations

    toxic elements and heavy metals

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

    chemical elements and compounds in scientific contexts, especially toxic or trace metals.

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

    The neuron identifies numeric expressions and measurements (quantities, values, and units) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     colorida
    -1.26
     escalier
    -1.18
    お昼
    -1.16
    もうすぐ
    -1.13
     utilisent
    -1.09
    饃
    -1.09
    お菓子
    -1.09
     rồi
    -1.07
     produisons
    -1.06
     delantero
    -1.05
    POSITIVE LOGITS
     in
    1.36
    használ
    1.19
     metals
    1.16
    χυ
    1.13
    állítás
    1.11
     känner
    1.07
    őre
    1.07
    ֺ
    1.03
    rões
    1.03
    พาะ
    1.02
    Activations Density 0.137%

    No Known Activations