© 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. 22-GEMMASCOPE-RES-131K
    7. 54303
    Prev
    Next
    INDEX
    Explanations

    new or unfamiliar situations

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

    The neuron fires strongly on words and phrases that describe transitions into new or unfamiliar situations or environments.

    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
     currently
    -1.10
     if
    -1.10
     question
    -1.09
     by
    -1.08
     oggi
    -1.07
     concluded
    -1.01
     you
    -1.00
     actualmente
    -1.00
     atualmente
    -0.99
     should
    -0.98
    POSITIVE LOGITS
     new
    2.53
     unfamiliar
    1.78
    新的
    1.70
     different
    1.59
    เปลี่ยน
    1.52
    new
    1.48
    新しい
    1.48
     nowych
    1.47
    ใหม่
    1.47
    neue
    1.41
    Activations Density 0.041%

    No Known Activations