© 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. 12985
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    The neuron detects time‐code patterns (numeric timestamps with colons, e.g. “[00:18]”).

    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
     Must
    -0.90
     if
    -0.89
    S
    -0.89
    n
    -0.88
    f
    -0.88
    UDIO
    -0.88
    Bigr
    -0.87
     to
    -0.84
    A
    -0.84
    P
    -0.84
    POSITIVE LOGITS
     Twp
    1.24
    Muerte
    1.11
    鈥
    1.10
    Ingrédients
    1.09
    还有
    1.06
    Bjs
    1.06
    Penjelasan
    1.05
     amortigu
    1.03
    Berat
    1.03
     ۱۴۰۰
    1.02
    Activations Density 0.000%

    No Known Activations