© 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. 34-GEMMASCOPE-RES-131K
    4. 119266
    Prev
    Next
    INDEX
    Explanations

    online discussion and editing

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

    The neuron is a detector for very common high‐frequency “stop” words (e.g. the, is, to, I, what) rather than any particular meaning.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ایای
    -0.98
    都
    -0.97
     recyclerView
    -0.96
    й
    -0.94
    !*\
    -0.93
    >|</
    -0.92
    >(&
    -0.88
    :\/\/
    -0.88
    !!!”
    -0.88
     Covid
    -0.88
    POSITIVE LOGITS
     wiki
    1.47
     discussion
    1.41
     문서
    1.40
     wik
    1.30
     vandalism
    1.27
    wiki
    1.20
     Diskussion
    1.18
     editors
    1.18
     vandal
    1.15
    条目
    1.14
    Activations Density 0.103%

    No Known Activations