© 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. 62537
    Prev
    Next
    INDEX
    Explanations

    inverse and inverted concepts

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

    The neuron detects occurrences of words built on the “inver-” root (e.g. inverse, inversion, inverted).

    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
     entrambi
    -0.93
     advance
    -0.92
    WW
    -0.82
    そこに
    -0.82
     advances
    -0.82
     ungewöhn
    -0.78
    straint
    -0.77
        
    -0.77
    2
    -0.76
     nominally
    -0.75
    POSITIVE LOGITS
     commas
    1.14
    鰨
    0.93
     merak
    0.92
     polarity
    0.91
    🤒
    0.89
    ♡♡
    0.87
    摃
    0.86
    ✋
    0.85
     appris
    0.83
    kkk
    0.83
    Activations Density 0.015%

    No Known Activations