© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14591
    Prev
    Next
    INDEX
    Explanations

    sphingosine, MTV, Mitch

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

    The neuron activates on biochemical terms beginning with “sph,” i.e. sphingolipid‐related words.

    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
    _{
    -2.61
    觏
    -2.52
    镠
    -2.41
    薆
    -2.38
    鰾
    -2.25
    沇
    -2.25
    ){
    
    -2.25
    ная
    -2.20
     europea
    -2.19
    ྥ
    -2.19
    POSITIVE LOGITS
    transQ
    2.64
     THERE
    2.47
     peuvent
    2.42
    s
    2.36
     chief
    2.34
    ?"
    2.31
     been
    2.31
    みたら
    2.25
    engono
    2.23
     suoi
    2.20
    Activations Density 0.004%

    No Known Activations