© 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. 108300
    Prev
    Next
    INDEX
    Explanations

    experimental observations

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

    Explanation of neuron 4 behavior: the main thing this neuron does is detect highly technical, domain-specific terms and phrases typical of condensed-matter physics research abstracts.

    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
    tiez
    -0.93
     tijdens
    -0.88
    рость
    -0.86
     الحكومة
    -0.86
     włos
    -0.85
    CartItem
    -0.82
    ଶ
    -0.82
    ṓ
    -0.82
    soe
    -0.82
     био
    -0.81
    POSITIVE LOGITS
    DOS
    1.09
     ادبی
    1.07
     DOS
    0.99
     Frie
    0.96
     insulating
    0.94
     thermometer
    0.94
     BCS
    0.93
     temperature
    0.92
     Mott
    0.92
     Kondo
    0.91
    Activations Density 0.119%

    No Known Activations