© 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. 113483
    Prev
    Next
    INDEX
    Explanations

    phospho-lipid/protein/inositol/creatine contexts

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

    The neuron detects mentions of phospholipids in scientific texts about cell membranes and biochemistry.

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

    The neuron consistently activates on the subword “phospho” (i.e. the prefix “phospho-” in technical terms).

    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
    有三
    -2.28
     intenta
    -2.27
    他们的
    -2.16
    ⟝
    -2.06
    䜣
    -2.05
    genodigd
    -2.02
    slavery
    -1.98
    "",
    
    -1.97
     comparte
    -1.95
     accedi
    -1.95
    POSITIVE LOGITS
    ка
    2.81
    Ꭳ
    2.42
    و
    2.31
     implemented
    2.22
    ྥ
    2.19
    beiros
    2.13
    ጧ
    2.13
    ли
    2.11
    да
    2.05
    薷
    2.05
    Activations Density 0.007%

    No Known Activations