© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106480
    Prev
    Next
    INDEX
    Explanations

    condensed matter physics

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

    The neuron fires on occurrences of the phrase “condensed matter,” i.e. tokens making up “condensed” and “matter.”

    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
     on
    -0.88
    貯
    -0.84
     eye
    -0.80
     Players
    -0.80
     Va
    -0.79
    eye
    -0.78
     Johnson
    -0.75
     còn
    -0.74
     userRepository
    -0.74
    WebApplication
    -0.73
    POSITIVE LOGITS
     matter
    1.21
     Matter
    1.04
    Matter
    1.03
     cond
    0.92
    matter
    0.89
     MATTER
    0.88
    нием
    0.85
    емости
    0.84
     sirens
    0.83
     convoy
    0.83
    Activations Density 0.001%

    No Known Activations