© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34350
    Prev
    Next
    INDEX
    Explanations

    rapidly changing world

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

    The neuron consistently activates on terms that describe change, transformation, or dynamic shifts (e.g. shifting, changing, evolving, revolutionizing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ਞ
    -1.30
     褲
    -1.23
    יפור
    -1.21
    rifft
    -1.17
     patate
    -1.16
    OfWeek
    -1.16
     سریال
    -1.16
    鱨
    -1.14
    timme
    -1.14
     موسیقی
    -1.13
    POSITIVE LOGITS
     changes
    2.08
     changing
    1.79
     new
    1.79
     change
    1.77
     changed
    1.67
     rapidly
    1.55
    :
    1.49
     global
    1.42
     trends
    1.40
     we
    1.34
    Activations Density 0.045%

    No Known Activations