© 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. 34-GEMMASCOPE-RES-131K
    4. 84892
    Prev
    Next
    INDEX
    Explanations

    neutrino mass and oscillation

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

    The neuron is selectively activated by dense physics‐paper jargon and notation—especially technical terms like “tachyonic,” “neutrino,” “mass state,” and embedded numeric or formulaic tokens.

    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
     squamous
    -0.89
     Paulo
    -0.74
     Jalisco
    -0.72
     disks
    -0.71
    Servers
    -0.71
     booms
    -0.70
     Tulip
    -0.70
    👖
    -0.69
     Hov
    -0.69
    gesch
    -0.69
    POSITIVE LOGITS
     neutrino
    2.98
     neutrinos
    2.75
     Neu
    2.16
    Neu
    2.14
     Neutr
    1.98
    neu
    1.98
     neu
    1.33
     NEU
    1.16
    ν
    1.12
    NEU
    1.09
    Activations Density 0.045%

    No Known Activations