© 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. 98343
    Prev
    Next
    INDEX
    Explanations

    self-esteem and confidence

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

    The neuron detects mentions of one’s sense of self—especially words about self-esteem, self-confidence, self-image, and related “self-” constructs.

    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
     to
    -1.42
     of
    -1.05
     still
    -1.02
    駅から
    -0.99
    ft
    -0.98
    ),
    -0.98
     such
    -0.96
    所示
    -0.95
    dist
    -0.94
    cost
    -0.94
    POSITIVE LOGITS
     confidence
    1.88
    Confidence
    1.70
    confidence
    1.66
     Confidence
    1.66
     tráiler
    1.30
    自信
    1.27
     helicóptero
    1.26
     self
    1.21
     confiance
    1.16
     confident
    1.16
    Activations Density 0.016%

    No Known Activations