© 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. 130542
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of cameo or guest appearances (e.g. “cameo,” “appearance,” “guest”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    cameo and guest appearances

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     okre
    -1.12
     EXHIB
    -1.10
     मोबाइल
    -1.05
     collègues
    -1.02
     gmin
    -1.00
     nowo
    -0.99
    styrelsen
    -0.97
    bedarf
    -0.96
    囔
    -0.96
     überweisen
    -0.94
    POSITIVE LOGITS
     cameo
    1.65
    íguez
    1.43
     appearances
    1.35
     appearance
    1.31
    scaleY
    1.23
     as
    1.20
     guest
    1.20
     in
    1.20
     حضور
    1.20
     brief
    1.19
    Activations Density 0.036%

    No Known Activations