© 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. 101582
    Prev
    Next
    INDEX
    Explanations

    Psi4 / PSI

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

    references to PSI (Physics or scientific notation) and similar scientific acronyms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the token "psi" (case-insensitive), particularly in technical, scientific, or code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron primarily detects occurrences of the substring “psi” (often as part of technical or code identifiers).

    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
     They
    -3.48
     nová
    -2.77
     новая
    -2.75
    慜
    -2.75
    遄
    -2.70
    鸶
    -2.66
    屜
    -2.58
     “[
    -2.55
     rampant
    -2.50
     enigmatic
    -2.48
    POSITIVE LOGITS
    {
    2.73
     можешь
    2.56
    鹛
    2.42
    筇
    2.34
    но
    2.22
     didik
    2.20
     ltd
    2.20
            
    2.19
     barcel
    2.19
    ar
    2.17
    Activations Density 0.003%

    No Known Activations