© 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. 12978
    Prev
    Next
    INDEX
    Explanations

    time since / duration / past events

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

    This neuron detects mentions of numerical records or superlative sports statistics (e.g. biggest, highest, worst, margins, scoring, streaks).

    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
     herida
    -0.92
    приклад
    -0.86
    ID
    -0.82
    这些
    -0.82
    ᥙ
    -0.81
    .
    -0.79
    çak
    -0.79
    ality
    -0.78
    html
    -0.78
     .
    -0.76
    POSITIVE LOGITS
     whiteColor
    1.09
    ப்பட்டது
    0.96
    あらゆる
    0.92
    Inventario
    0.91
    oltre
    0.91
     last
    0.89
     історі
    0.89
    usahaan
    0.88
     other
    0.88
    щения
    0.88
    Activations Density 0.024%

    No Known Activations