© 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. 8210
    Prev
    Next
    INDEX
    Explanations

    hydrophilic polymers and interaction

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

    The neuron detects terms related to the chemical property of "hydrophilic" or water-loving substances.

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

    The neuron strongly activates on the word “hydrophilic,” i.e. on references to hydrophilicity in technical contexts.

    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
    槼
    -3.28
    踽
    -3.09
    犼
    -3.00
    焢
    -2.97
    笮
    -2.84
     nahil
    -2.80
    餍
    -2.78
    踯
    -2.78
     夜景
    -2.77
    茕
    -2.75
    POSITIVE LOGITS
    ing
    3.53
     them
    3.16
    They
    3.08
    It
    3.06
    .
    3.00
     You
    2.88
    You
    2.86
    ة
    2.78
    --
    2.73
    独特
    2.70
    Activations Density 0.016%

    No Known Activations