© 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. 10-GEMMASCOPE-RES-131K
    7. 105673
    Prev
    Next
    INDEX
    Explanations

    clauses starting with if

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

    the word "if" when it begins a conditional clause or hypothetical scenario.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron responds to the subordinating conjunction “if,” i.e. 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_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
     également
    -1.78
     They
    -1.77
     &
    -1.68
     
    -1.59
     myös
    -1.47
     either
    -1.46
     также
    -1.44
     також
    -1.41
     زیرا
    -1.41
     also
    -1.38
    POSITIVE LOGITS
    entlig
    1.80
    arakhand
    1.53
    য়ে
    1.53
    hauled
    1.53
    </strong>
    1.50
    Ｉ
    1.50
    isait
    1.49
    ajú
    1.45
    InjectAttribute
    1.45
    ке
    1.45
    Activations Density 0.018%

    No Known Activations