© 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. 56700
    Prev
    Next
    INDEX
    Explanations

    boiling melting freezing points

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

    discussions of temperature and melting/boiling points in scientific contexts.

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

    The neuron fires primarily on numeric values, especially measurements and other numbers.

    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
    ცი
    -0.78
    blasts
    -0.71
    超
    -0.69
    meng
    -0.69
    电话
    -0.69
     gegen
    -0.68
    blas
    -0.68
     الموقع
    -0.67
    基本
    -0.66
    完全
    -0.66
    POSITIVE LOGITS
     boiling
    2.64
     melting
    2.56
     Melting
    1.99
    Melting
    1.84
    boiling
    1.83
     Boiling
    1.80
    Boiling
    1.73
    melting
    1.67
     freezing
    1.58
     boils
    1.47
    Activations Density 0.025%

    No Known Activations