© 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. 34-GEMMASCOPE-RES-131K
    4. 81159
    Prev
    Next
    INDEX
    Explanations

    outfits for occasions

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

    The main thing this neuron does is identify numeric tokens (e.g., years, list indices, prices, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     familiare
    -0.88
    ITIS
    -0.87
     cristi
    -0.85
    ilets
    -0.84
    pography
    -0.84
    记载
    -0.83
    ファイル
    -0.82
    ppp
    -0.81
     instala
    -0.81
    berto
    -0.81
    POSITIVE LOGITS
     casual
    2.03
     Casual
    1.61
    casual
    1.59
    Casual
    1.44
     informal
    1.31
     errands
    1.30
     everyday
    1.29
     causal
    1.27
     office
    1.21
     attending
    1.21
    Activations Density 0.038%

    No Known Activations