© 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. 106359
    Prev
    Next
    INDEX
    Explanations

    abandonment cost

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

    The neuron fires on the structured numeric and place/time details typical of an obituary notice (ages, dates, times, and locations).

    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
    emptyList
    -0.80
    上下
    -0.77
    ɒ
    -0.76
    ℳ
    -0.76
     gleiche
    -0.74
    yafet
    -0.73
     Traverse
    -0.73
    owią
    -0.72
     Schülerinnen
    -0.72
    __('
    -0.71
    POSITIVE LOGITS
     Hager
    0.84
     Cumberland
    0.81
     деле
    0.81
     allá
    0.80
    сован
    0.79
    madamente
    0.77
     Pw
    0.75
    STATEMENT
    0.74
    Hust
    0.73
     Gettysburg
    0.72
    Activations Density 0.017%

    No Known Activations