© 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. 106434
    Prev
    Next
    INDEX
    Explanations

    plastic/soil compounds

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

    technical terms in scientific and engineering texts, particularly relating to soil, materials, and geological properties.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting numeric tokens and quantitative measurements in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ドリ
    -0.78
    効果
    -0.75
    志愿
    -0.74
    RTLI
    -0.73
     Sandra
    -0.72
    Изо
    -0.71
    焦
    -0.69
     уров
    -0.69
    umna
    -0.68
    риев
    -0.68
    POSITIVE LOGITS
     plasticity
    1.29
     PLASTIC
    1.08
     Plastic
    1.05
    Plastic
    1.04
     soil
    0.89
     plastic
    0.89
    Engineering
    0.85
     engineering
    0.84
    plastic
    0.84
     soils
    0.82
    Activations Density 0.008%

    No Known Activations