© 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. 99012
    Prev
    Next
    INDEX
    Explanations

    nuclear measurements and comparisons

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

    The neuron strongly responds to technical, nuclear‐physics experimental language—especially terms describing measurements (e.g. beta‐decay, gamma‐ray emission, detectors, probe, shell‐model calculations).

    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
    žd
    -0.98
    glyph
    -0.93
    Glyph
    -0.93
    LogManager
    -0.85
     alleles
    -0.82
    Depot
    -0.82
     நீ
    -0.82
    enso
    -0.82
     الحكومة
    -0.80
    mą
    -0.79
    POSITIVE LOGITS
     nuclear
    1.33
    nuclear
    1.24
    ggling
    1.23
     Nuclear
    1.13
    nucleus
    1.05
    Nuclear
    1.05
     NUCLEAR
    1.01
    keV
    1.01
    uclear
    1.00
     keV
    1.00
    Activations Density 0.036%

    No Known Activations