© 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. 98479
    Prev
    Next
    INDEX
    Explanations

    who we are

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

    The neuron fires strongly on words that signal identity or existence statements—pronouns and verbs used to define “who/what someone or something is.”

    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
     its
    -1.45
    them
    -1.21
     their
    -1.09
     Them
    -1.05
     theres
    -0.96
     Its
    -0.92
     THEM
    -0.90
    Its
    -0.90
     свою
    -0.88
     ennek
    -0.87
    POSITIVE LOGITS
     they
    1.27
     we
    0.92
    ってしまった
    0.90
     she
    0.89
    前で
    0.87
    ったので
    0.87
     chré
    0.85
     ontvang
    0.80
    单纯
    0.80
    有问题
    0.79
    Activations Density 0.030%

    No Known Activations