© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    soluble compounds or fractions

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

    The neuron detects the word "soluble" in scientific contexts, particularly in biochemistry and materials science.

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

    The neuron consistently picks out occurrences of the adjective “soluble.”

    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
     ſont
    -2.94
    ſche
    -2.92
    翃
    -2.67
    
    -2.66
    桖
    -2.52
     they
    -2.41
    踭
    -2.36
    噌
    -2.31
     were
    -2.28
    僦
    -2.28
    POSITIVE LOGITS
    \
    2.94
    Y
    2.83
    P
    2.81
    izing
    2.81
    勍
    2.67
    蛧
    2.56
    鋱
    2.53
    8
    2.50
    ୌ
    2.48
    3
    2.34
    Activations Density 0.014%

    No Known Activations