© 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. 84257
    Prev
    Next
    INDEX
    Explanations

    actor names after "as"

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

    The neuron detects the use of “as” when introducing an actor’s role in cast listings.

    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
     that
    -1.28
    t
    -1.12
    aliers
    -1.09
    M
    -1.07
     wenigstens
    -1.04
     after
    -1.03
     folgender
    -1.03
     verksam
    -1.02
     raíz
    -1.02
     uses
    -1.02
    POSITIVE LOGITS
     the
    1.47
    characters
    1.33
    merken
    1.22
    paket
    1.20
    ınd
    1.20
     faca
    1.18
     personaje
    1.17
    źródło
    1.16
    junge
    1.15
     zoude
    1.14
    Activations Density 0.034%

    No Known Activations