© 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. 54326
    Prev
    Next
    INDEX
    Explanations

    noun states or objects

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

    The neuron strongly activates on content nouns—especially concrete or uncommon object-words in the text.

    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
     conftest
    -1.07
     acqua
    -1.02
     avocat
    -1.01
    factorial
    -0.98
     ergonom
    -0.96
    沵
    -0.96
    蕎麦
    -0.95
     trésor
    -0.94
    anians
    -0.91
     discipl
    -0.90
    POSITIVE LOGITS
     people
    1.45
     other
    1.34
     first
    1.13
     only
    1.12
     became
    1.06
     become
    1.05
     remained
    1.05
     numerous
    1.05
     continued
    1.05
     on
    1.04
    Activations Density 0.050%

    No Known Activations