© 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. 9360
    Prev
    Next
    INDEX
    Explanations

    ability to

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

    The neuron specifically detects occurrences of the word “ability.”

    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
    𞤢
    -2.72
    妧
    -2.70
    硨
    -2.53
    
    -2.45
     tesettür
    -2.45
    鷓
    -2.44
    ことなく
    -2.42
    俛
    -2.42
    ︲
    -2.41
    AMILTON
    -2.39
    POSITIVE LOGITS
     to
    3.11
     It
    2.73
     This
    2.59
    {
    2.53
    ↵↵
    2.52
     有
    2.50
     Would
    2.47
     Definitely
    2.34
     Unfortunately
    2.31
     There
    2.27
    Activations Density 0.018%

    No Known Activations