© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34866
    Prev
    Next
    INDEX
    Explanations

    equivalent units and measurements

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

    This neuron detects terms related to quantitative measurement and evaluation (e.g., titration, quantification, concentration, values, equivalents).

    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
     esquerdo
    -0.78
    projectile
    -0.75
    qty
    -0.72
    dropout
    -0.71
     proud
    -0.71
    布
    -0.71
    Filmography
    -0.69
    approve
    -0.69
     profits
    -0.69
    Superview
    -0.68
    POSITIVE LOGITS
     Equivalent
    1.53
     equivalent
    1.53
     equivalence
    1.48
     equivalents
    1.42
    Equivalent
    1.40
     Equi
    1.31
     équi
    1.27
     equival
    1.24
     units
    1.20
    equivalent
    1.18
    Activations Density 0.080%

    No Known Activations