© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72869
    Prev
    Next
    INDEX
    Explanations

    coming events and sequences

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

    The neuron flags occurrences of the word “coming,” especially in contexts announcing upcoming events.

    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
    倬
    -1.33
     Anadolu
    -1.27
    的一次
    -1.21
    “
    -1.21
     favoritas
    -1.18
     взял
    -1.15
     あり
    -1.14
     取り
    -1.13
     gik
    -1.11
    ными
    -1.10
    POSITIVE LOGITS
     coming
    1.71
     Coming
    1.45
     Soon
    1.34
     approaching
    1.29
    聼
    1.23
     soon
    1.21
     upcoming
    1.20
    嫫
    1.20
     entering
    1.20
    COMING
    1.14
    Activations Density 0.047%

    No Known Activations