© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44647
    Prev
    Next
    INDEX
    Explanations

    inspection of objects and apparatus

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

    The neuron fires on occurrences of the word “inspection,” especially in formal or technical/descriptive headings.

    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
    琑
    -2.91
    er
    -2.78
    TemporalType
    -2.72
    瓩
    -2.55
    
    -2.52
     exacting
    -2.48
     办
    -2.36
    参数
    -2.30
    猟
    -2.25
    道の
    -2.23
    POSITIVE LOGITS
    ஂ
    3.72
    哢
    3.03
     để
    2.94
    鈇
    2.89
    踅
    2.86
    鄠
    2.84
    ㈮
    2.75
    1
    2.64
    ⬮
    2.63
    儈
    2.61
    Activations Density 0.003%

    No Known Activations