© 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. 10-GEMMASCOPE-RES-131K
    7. 15796
    Prev
    Next
    INDEX
    Explanations

    rock formations and strata

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

    The neuron strongly activates on the word “rock” (and closely related geological formation terms).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵
    -1.80
     uruguay
    -1.66
     ecuador
    -1.63
     Nº
    -1.63
    ieważ
    -1.56
    7
    -1.54
     uwe
    -1.54
    </h2>
    -1.51
     huf
    -1.51
     luxem
    -1.49
    POSITIVE LOGITS
     Ofrece
    1.93
    ffiti
    1.81
     เมื่อ
    1.70
     большой
    1.70
     generó
    1.68
     крепления
    1.66
     desagrad
    1.63
     tratado
    1.61
     especias
    1.61
     diversas
    1.60
    Activations Density 0.033%

    No Known Activations