© 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. 36024
    Prev
    Next
    INDEX
    Explanations

    as a or an

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

    The neuron detects “as a” (and “as an”) constructions introducing a role or capacity.

    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
     they
    -1.60
     that
    -1.37
    aliers
    -1.27
     make
    -1.20
     if
    -1.19
    Tradu
    -1.19
     take
    -1.16
    了一些
    -1.15
     for
    -1.14
    多少钱
    -1.13
    POSITIVE LOGITS
     a
    2.39
    AGEMENT
    1.34
     an
    1.29
     anúncio
    1.29
     acidente
    1.27
     pacote
    1.26
     növény
    1.25
     både
    1.20
     aparelho
    1.17
     xadrez
    1.16
    Activations Density 0.050%

    No Known Activations