© 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. 71429
    Prev
    Next
    INDEX
    Explanations

    enclosing items or areas

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

    The neuron detects dictionary- or encyclopedia-style definitional statements (i.e. “X is a Y…” descriptions).

    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
     each
    -1.70
     only
    -1.64
     every
    -1.62
     like
    -1.50
    וּ
    -1.49
    ּוֹ
    -1.35
     three
    -1.34
     totally
    -1.31
     five
    -1.30
     all
    -1.28
    POSITIVE LOGITS
     boken
    1.38
    ἵ
    1.37
     kawaida
    1.37
     tumbuhan
    1.32
    ୀ
    1.30
     hvad
    1.29
     anúncios
    1.23
    ={
    1.23
     باسلام
    1.23
    通常
    1.20
    Activations Density 0.370%

    No Known Activations