© 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. 69531
    Prev
    Next
    INDEX
    Explanations

    why would

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

    The neuron detects conditional or hypothetical constructions signaled by the modal “would” (including contracted “’d”) in statements or questions.

    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
     about
    -1.79
    ꙰
    -1.41
     vigente
    -1.30
    レーター
    -1.23
     acondicionado
    -1.23
    の準備
    -1.18
     delicada
    -1.17
    بالإنجليزية
    -1.16
    vyš
    -1.15
     instead
    -1.14
    POSITIVE LOGITS
     such
    1.40
    这样的
    1.29
    such
    1.24
    Such
    1.19
    摑
    1.18
     ...
    1.16
     چنین
    1.10
    ...@
    1.09
     Celebr
    1.09
     SUCH
    1.09
    Activations Density 0.031%

    No Known Activations