© 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. 47673
    Prev
    Next
    INDEX
    Explanations

    questions starting with why or does

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

    The neuron picks out numeric values (literal numbers and decimals) within code‐ or JSON‐like 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_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
    pullover
    -1.60
    🩱
    -1.59
    LEBR
    -1.45
     cuillère
    -1.34
    DEPORT
    -1.30
     utafiti
    -1.26
    方で
    -1.23
    紧接着
    -1.22
     और
    -1.20
     этой
    -1.20
    POSITIVE LOGITS
     what
    1.46
    What
    1.45
     古着
    1.41
    kuš
    1.39
     moeili
    1.39
    だが
    1.39
     haría
    1.38
    诟
    1.38
     beneficial
    1.37
     different
    1.34
    Activations Density 0.000%

    No Known Activations