© 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. 67178
    Prev
    Next
    INDEX
    Explanations

    personal possessions or actions

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

    The neuron fires on first‐ and second‐person possessive tokens (e.g. “my,” “your,” “first”).

    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
    去做
    -1.12
     acestei
    -1.11
     is
    -1.11
    ਗ਼
    -1.04
    把自己
    -1.04
    providing
    -1.03
    hike
    -1.02
    increase
    -0.99
    Yes
    -0.99
     acestui
    -0.98
    POSITIVE LOGITS
     each
    1.46
    bicara
    1.22
     from
    1.20
     one
    1.17
     that
    1.16
     Terbaru
    1.13
    Cela
    1.08
     there
    1.07
     prad
    1.07
     bandou
    1.06
    Activations Density 0.029%

    No Known Activations