© 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. 110536
    Prev
    Next
    INDEX
    Explanations

    counting words after the

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

    the word "The" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on numeric quantitative values—especially statistical figures, measurements, or decimal‐formatted numbers.

    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
    ₃
    -1.46
    ','#
    -1.36
    entrums
    -1.36
     clínicos
    -1.30
     at
    -1.30
    着一个
    -1.29
    ваем
    -1.27
    ꜆
    -1.27
    >"+
    -1.26
     querida
    -1.25
    POSITIVE LOGITS
    鈊
    1.56
     tendremos
    1.45
    Zubereitung
    1.43
     entweder
    1.36
     YOU
    1.34
    翆
    1.34
     empie
    1.33
     individuelle
    1.32
    ➬
    1.32
    たぶん
    1.31
    Activations Density 0.129%

    No Known Activations