© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7009
    Prev
    Next
    INDEX
    Explanations

    if questions or clauses

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

    The neuron strongly activates on occurrences of the word “if,” signaling conditional clauses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    iramente
    -1.55
     них
    -1.53
     nicht
    -1.40
    them
    -1.38
     tidak
    -1.37
    lighed
    -1.36
     если
    -1.32
     modele
    -1.32
    archiwizowane
    -1.30
    paedia
    -1.30
    POSITIVE LOGITS
     there
    4.22
     it
    3.64
     they
    2.55
     any
    2.33
     anyone
    2.16
     this
    2.11
     anything
    1.98
     we
    1.78
     you
    1.77
     indeed
    1.72
    Activations Density 0.033%

    No Known Activations