© 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. 90727
    Prev
    Next
    INDEX
    Explanations

    UI elements and identifiers

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

    The neuron is triggered by code and XML identifier tokens (e.g. variable/class names or id attributes).

    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
     「
    -1.70
     contenedores
    -1.61
     kupić
    -1.60
     récla
    -1.59
     hés
    -1.58
     réve
    -1.56
     circon
    -1.56
     angen
    -1.55
     mélanger
    -1.55
     manquer
    -1.55
    POSITIVE LOGITS
     for
    3.09
     with
    2.83
     from
    2.52
     if
    2.42
     both
    2.41
     when
    2.36
     to
    2.34
     while
    2.30
     without
    2.17
     despite
    2.05
    Activations Density 0.002%

    No Known Activations