© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84413
    Prev
    Next
    INDEX
    Explanations

    Today's context

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

    This neuron fires on expository lead-in sentences that begin with “Today,” followed by a subject doing something (e.g. “Today, the Internet has…,” “Today, RNA is…”).

    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
     this
    -1.63
     recently
    -1.62
     altijd
    -1.45
     earlier
    -1.37
     siempre
    -1.34
     soon
    -1.33
     nikdy
    -1.30
     subsequently
    -1.30
     ultimately
    -1.29
     initially
    -1.29
    POSITIVE LOGITS
    still
    1.16
    thanks
    1.14
    Nowadays
    1.13
     still
    1.13
    Still
    1.12
    Fortunately
    1.09
    mainly
    1.03
    Unless
    1.02
    almost
    1.02
    Thanks
    1.01
    Activations Density 0.046%

    No Known Activations