© 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. 47142
    Prev
    Next
    INDEX
    Explanations

    missing everyday things

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

    The neuron fires on words that express longing or yearning (e.g. “miss,” “missing,” “crave”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     to
    -1.18
     gefertigt
    -0.91
     mehrfach
    -0.87
     beschränkt
    -0.85
     wiederhol
    -0.82
     victory
    -0.82
     success
    -0.81
    Fernsehserie
    -0.81
     recently
    -0.78
     differing
    -0.78
    POSITIVE LOGITS
     terribly
    1.46
     sorely
    1.36
     absence
    1.15
    everyday
    1.15
     dearly
    1.11
     chyb
    1.06
     Absence
    1.05
    Missing
    1.05
    poke
    1.04
     everyday
    1.03
    Activations Density 0.006%

    No Known Activations