© 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. 28481
    Prev
    Next
    INDEX
    Explanations

    community purpose, contribution, or growth

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

    The neuron fires on language that issues an open invitation or welcome—phrases about opening doors to bring people together for community events.

    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
    ᐈ
    -1.41
    部份
    -1.38
    ༎
    -1.29
     épices
    -1.27
    tså
    -1.27
     banget
    -1.25
    Garantía
    -1.24
     laine
    -1.24
    imágenes
    -1.23
     éta
    -1.22
    POSITIVE LOGITS
     ajuta
    1.30
     również
    1.29
     this
    1.25
    ﷲ
    1.23
    互相
    1.22
     Ortschaft
    1.20
     наша
    1.13
     또
    1.12
     our
    1.11
    個室
    1.11
    Activations Density 0.057%

    No Known Activations