© 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. 10-GEMMASCOPE-RES-131K
    4. 10343
    Prev
    Next
    INDEX
    Explanations

    every followed by a noun

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

    This neuron detects occurrences of the word “Every” when it introduces a recurring time or frequency expression (e.g. “Every day,” “Every time,” “Every year”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -2.17
    f
    -1.81
     incluyendo
    -1.75
    <td>
    -1.74
    以免
    -1.73
    c
    -1.72
     which
    -1.64
    8
    -1.62
     including
    -1.62
     is
    -1.60
    POSITIVE LOGITS
    Zubereitung
    1.90
    providedIn
    1.70
    borderSide
    1.64
    AppComponent
    1.61
    ȶ
    1.60
    Kemudian
    1.60
    appBar
    1.60
    eyes
    1.58
    푘
    1.57
    紱
    1.55
    Activations Density 0.023%

    No Known Activations