© 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. 99895
    Prev
    Next
    INDEX
    Explanations

    aliphatic, eddy, salinity

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

    The neuron identifies chemistry-related terms, with a strong activation for "aliphatic" and other technical scientific or chemical terms.

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

    the neuron strongly activates on the chemical term “aliphatic,” marking occurrences of that descriptor.

    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
    ?”
    -3.67
    ”
    -3.41
     ”
    -3.38
    
    -3.30
    .”
    -3.13
    ...”
    -2.89
    -”
    -2.89
    —”
    -2.75
     “(
    -2.70
     dreht
    -2.70
    POSITIVE LOGITS
    鑪
    2.98
    旆
    2.95
    桄
    2.81
    ⍢
    2.75
    ︓
    2.72
     It
    2.69
    e
    2.63
    瑨
    2.52
    了你
    2.50
    眼下
    2.48
    Activations Density 0.026%

    No Known Activations