© 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. 79822
    Prev
    Next
    INDEX
    Explanations

    socialist German, sub-atomic particle, preventing vitamin

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

    The neuron is primarily triggered by domain‐specific technical or scholarly terms and proper nouns (often accompanied by detailed numbers), such as specialized jargon, academic names, and specific concepts.

    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
    たぶん
    -1.24
     реально
    -1.17
     אלה
    -1.15
    をします
    -1.13
     storie
    -1.13
     dévelo
    -1.13
     abrazo
    -1.12
    𝘶
    -1.10
     eseguire
    -1.10
     accedere
    -1.10
    POSITIVE LOGITS
     poliéster
    1.48
     (
    1.45
    tempat
    1.27
    Anyways
    1.26
    Alright
    1.24
    ském
    1.23
    gucigalpa
    1.22
     skvě
    1.21
    もありました
    1.21
    Whatsapp
    1.21
    Activations Density 0.059%

    No Known Activations