© 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. 115931
    Prev
    Next
    INDEX
    Explanations

    in a broad sense

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

    The neuron fires on prepositional “in” phrases that introduce a domain or sense qualifier (e.g. “in the SQL language,” “in a broad sense,” “in the narrow sense”).

    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
    ENDE
    -0.78
     пальто
    -0.77
    ende
    -0.75
    minente
    -0.73
    𝓘
    -0.72
    itati
    -0.71
    Ceiling
    -0.71
     hidrat
    -0.71
    tiere
    -0.71
     SYLLABLE
    -0.71
    POSITIVE LOGITS
     sense
    7.75
    sense
    5.75
     Sense
    4.94
    Sense
    4.94
     sentido
    4.31
     SENSE
    3.86
     senses
    3.66
     senso
    3.06
     смысле
    2.94
     sensed
    2.64
    Activations Density 0.060%

    No Known Activations