© 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. 71240
    Prev
    Next
    INDEX
    Explanations

    solubility

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

    references to the solubility of chemical compounds or substances.

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

    The neuron activates on mentions of a compound’s solubility (especially when paired with numeric values).

    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
     That
    -2.44
    "
    -2.42
    訁
    -2.20
     что
    -2.17
     ส์
    -2.11
    神
    -2.09
     You
    -2.06
    lük
    -2.05
     américains
    -2.05
    auteuil
    -2.03
    POSITIVE LOGITS
    “)
    2.45
    ”]
    2.36
    ——”
    2.25
    ~~~~~~~
    2.17
    ”，
    2.16
    “
    2.14
    )',
    2.14
    ”)
    2.13
    会出现
    2.13
    Y
    2.09
    Activations Density 0.003%

    No Known Activations