© 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. 22-GEMMASCOPE-RES-131K
    7. 39603
    Prev
    Next
    INDEX
    Explanations

    noun followed by verb or adjective

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

    This neuron activates on capitalized product, technology, or brand names (i.e. named technical entities).

    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
     this
    -1.40
     which
    -1.25
    ???:
    -1.14
    ƀ
    -1.13
    diese
    -1.12
     signifikan
    -1.09
    この
    -1.08
     habían
    -1.07
    ܖ
    -1.07
    zzzz
    -1.06
    POSITIVE LOGITS
     is
    1.28
     are
    1.27
     poly
    1.17
    nóstico
    1.13
     can
    1.09
     dé
    1.07
     compared
    1.06
    不可以
    1.03
     como
    0.99
     works
    0.97
    Activations Density 0.035%

    No Known Activations