© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56970
    Prev
    Next
    INDEX
    Explanations

    nighttime

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

    The main thing this neuron does is detect open‐class content words (nouns, verbs, adjectives, adverbs) rather than function or stopwords.

    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
    řit
    -0.95
    sube
    -0.85
     Kamer
    -0.79
     Kini
    -0.77
     sube
    -0.77
    euvre
    -0.77
     submenu
    -0.77
    äß
    -0.76
     gada
    -0.76
     ssl
    -0.75
    POSITIVE LOGITS
     night
    6.22
     nighttime
    4.88
    Night
    4.28
     Night
    4.22
    night
    4.16
     NIGHT
    3.84
    夜
    3.64
     nights
    3.53
     ночью
    3.50
     nocturnal
    3.44
    Activations Density 0.066%

    No Known Activations