© 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. 10-GEMMASCOPE-RES-131K
    7. 119594
    Prev
    Next
    INDEX
    Explanations

    common sense and sensible

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

    The neuron fires on mentions of practical judgment or “sense” language (e.g. common sense, sensible, good sense).

    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
     Their
    -2.09
     Such
    -2.02
     &#
    -1.85
     ​
    -1.84
     the
    -1.83
     considerados
    -1.82
     Then
    -1.80
     They
    -1.80
     havia
    -1.78
     vistos
    -1.78
    POSITIVE LOGITS
    斯的
    2.33
    or
    2.06
    You
    2.03
    U
    2.02
    ጴ
    2.00
    ach
    1.94
     خاصی
    1.91
    also
    1.91
    henswürdigkeiten
    1.84
    H
    1.84
    Activations Density 0.003%

    No Known Activations