© 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. 22-GEMMASCOPE-RES-131K
    7. 33017
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by continuation

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

    The neuron is triggered by longer, multi-syllable technical or scientific nouns (i.e. domain-specific jargon).

    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
     rése
    -0.93
    Questo
    -0.89
    Questa
    -0.88
     sqlSession
    -0.88
     работают
    -0.82
    äst
    -0.82
    łaści
    -0.82
    Capacidad
    -0.81
     comedia
    -0.80
     américains
    -0.80
    POSITIVE LOGITS
     Rouge
    0.83
     Its
    0.81
     between
    0.81
    F
    0.79
     Between
    0.79
    案
    0.78
     its
    0.78
    購物
    0.77
    between
    0.77
    ).-
    0.76
    Activations Density 0.033%

    No Known Activations