© 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. 10-GEMMASCOPE-RES-131K
    7. 12517
    Prev
    Next
    INDEX
    Explanations

    afraid of / to

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

    The neuron activates on tokens expressing fear (e.g., “afraid,” “scared”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     longstanding
    -2.02
           
    -1.95
     rudimentary
    -1.93
     frantic
    -1.91
     mildly
    -1.91
     Completely
    -1.91
     noteworthy
    -1.89
     haphazard
    -1.85
     troubling
    -1.85
    It
    -1.85
    POSITIVE LOGITS
    搋
    2.34
    ↵
    2.14
     aks
    1.99
    zelfde
    1.98
     baumwolle
    1.96
     ―――
    1.88
     rive
    1.85
    鐿
    1.84
     syste
    1.84
     dezelve
    1.82
    Activations Density 0.006%

    No Known Activations