© 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. 22-GEMMASCOPE-RES-131K
    4. 79942
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

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

    The neuron consistently lights up on specialized, domain-specific jargon—technical or professional terms rather than common everyday words.

    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
    และ
    -2.13
     และ
    -1.94
    や
    -1.75
     goofy
    -1.67
     vê
    -1.60
     flamboyant
    -1.53
     verhind
    -1.52
     både
    -1.51
     и
    -1.50
     usando
    -1.48
    POSITIVE LOGITS
     as
    2.31
     when
    2.11
     it
    2.03
     make
    2.00
     provides
    1.98
     give
    1.91
     Because
    1.90
     their
    1.89
     while
    1.88
     During
    1.86
    Activations Density 0.372%

    No Known Activations