© 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. 103403
    Prev
    Next
    INDEX
    Explanations

    temporal changes and evolution

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

    The neuron fires on words and phrases that describe scientific study design, measurement, and longitudinal research methods.

    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
    均匀
    -0.82
    ≙
    -0.80
    gleiche
    -0.76
    偶
    -0.75
    downarrow
    -0.74
    ħħ
    -0.73
    enosti
    -0.71
    จัด
    -0.71
     mogelijkheden
    -0.70
    upe
    -0.69
    POSITIVE LOGITS
     evolution
    3.63
     changes
    3.44
     change
    2.84
    evolution
    2.72
     dynamics
    2.70
     Evolution
    2.63
     evolución
    2.52
    changes
    2.50
     Changes
    2.48
    Changes
    2.41
    Activations Density 0.462%

    No Known Activations