© 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. 22-GEMMASCOPE-RES-131K
    7. 32912
    Prev
    Next
    INDEX
    Explanations

    days before holidays or closures

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

    The neuron flags mentions of days off, holidays, or closures (e.g. businesses/schools closing or being “off”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     recently
    -1.20
     possibilidades
    -1.12
     currently
    -1.11
     pomocou
    -1.11
     OGSÅ
    -1.04
    цій
    -1.03
    []=$
    -1.02
    ######
    -1.02
     constantly
    -1.01
    zheimer
    -1.01
    POSITIVE LOGITS
     afternoon
    1.30
     Monday
    1.27
    壁纸
    1.20
    businesses
    1.18
    unduh
    1.12
     Tuesday
    1.12
     morning
    1.12
     office
    1.09
     day
    1.09
     widespread
    1.09
    Activations Density 0.026%

    No Known Activations