© 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. 22-GEMMASCOPE-RES-131K
    7. 69126
    Prev
    Next
    INDEX
    Explanations

    clock times

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

    The neuron detects the preposition “at” when it introduces a specific time in a schedule or event listing.

    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
     WEEKS
    -1.21
     that
    -1.20
     WEEKLY
    -1.16
    与
    -1.14
    derived
    -1.14
     problemet
    -1.13
     و
    -1.11
     soon
    -1.10
    ization
    -1.09
    viseur
    -1.09
    POSITIVE LOGITS
    ⦑
    1.08
    理由は
    1.07
    VYMaps
    1.05
    Histor
    1.05
    Mí
    1.04
     around
    1.02
     insanlar
    1.02
     noon
    0.99
     tarihinde
    0.99
    🎞
    0.97
    Activations Density 0.009%

    No Known Activations