© 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. 90411
    Prev
    Next
    INDEX
    Explanations

    increase or cause 'why'

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

    The neuron primarily activates on question marks (i.e. the '?' punctuation marking 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
     to
    -1.50
    ˃
    -1.40
     innerhalb
    -1.22
     включая
    -1.13
     "
    -1.13
    example
    -1.12
     kanton
    -1.10
     aussieht
    -1.09
     fois
    -1.08
     zoals
    -1.08
    POSITIVE LOGITS
     when
    1.59
     this
    1.57
    encils
    1.56
    何故
    1.52
     vettor
    1.52
     these
    1.51
     estuche
    1.39
     cauza
    1.38
     Hecho
    1.34
     why
    1.34
    Activations Density 0.177%

    No Known Activations