© 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. 34-GEMMASCOPE-RES-131K
    7. 103516
    Prev
    Next
    INDEX
    Explanations

    actions or states of being

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

    The neuron strongly activates on personal pronouns (e.g., I, you, us, he, my, they) referring to people.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     abbin
    -0.97
     aujourd
    -0.89
    cxx
    -0.88
    这种
    -0.87
    就会
    -0.86
    大丈夫
    -0.84
     adatta
    -0.84
    观
    -0.84
     Jeśli
    -0.82
     dasarnya
    -0.81
    POSITIVE LOGITS
     imprud
    0.94
     while
    0.93
     positioned
    0.92
     discrete
    0.91
     ironic
    0.90
     whilst
    0.90
     aligned
    0.89
     discreet
    0.87
     contín
    0.86
     auxiliar
    0.85
    Activations Density 0.017%

    No Known Activations