© 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. 83450
    Prev
    Next
    INDEX
    Explanations

    ego, self, identity

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

    The neuron activates strongly on mentions of “ego” and related self-identity terms.

    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
    這樣的
    -0.79
     nonostante
    -0.76
     nachher
    -0.73
     開始
    -0.70
    ADDED
    -0.69
    越多
    -0.69
    IDENCE
    -0.69
     подписа
    -0.69
     attain
    -0.69
     broad
    -0.69
    POSITIVE LOGITS
    tistic
    1.32
     ego
    1.10
     Ego
    1.09
     boost
    1.07
    boost
    1.06
    tism
    1.06
    Ego
    1.03
    trip
    1.02
    tis
    0.98
     Erik
    0.98
    Activations Density 0.014%

    No Known Activations