© 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. 56690
    Prev
    Next
    INDEX
    Explanations

    words starting with "Tar"

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

    The neuron detects occurrences of the character sequence “Tar” (i.e. tokens beginning with “Tar”).

    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
    ură
    -0.88
    g
    -0.81
    場所は
    -0.79
    Palo
    -0.78
     kalem
    -0.75
     accidentes
    -0.75
    Snoo
    -0.73
    quero
    -0.72
    Alkal
    -0.72
     even
    -0.71
    POSITIVE LOGITS
    Tar
    1.36
     Tar
    1.31
     TAR
    1.13
    TAR
    0.95
     tar
    0.91
     Lleg
    0.87
    geted
    0.86
    isio
    0.84
    Accepted
    0.82
     fakty
    0.82
    Activations Density 0.015%

    No Known Activations