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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108917
    Prev
    Next
    INDEX
    Explanations

    noisy measurements or observations

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

    The neuron activates on technical terms referring to data, measurements, and statistical observations in scientific contexts.

    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
    GetRequest
    -0.85
    eavor
    -0.80
     парамет
    -0.73
    OTO
    -0.73
     üst
    -0.73
    рку
    -0.73
    дмила
    -0.73
     Marge
    -0.73
     Edad
    -0.72
     emoc
    -0.71
    POSITIVE LOGITS
     observations
    2.56
     measurements
    2.53
     observed
    2.23
     observation
    2.20
    observations
    1.98
     measurement
    1.95
    Observation
    1.95
     Observations
    1.94
     Measurements
    1.93
     Observation
    1.91
    Activations Density 0.046%

    No Known Activations