© 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. 10-GEMMASCOPE-RES-131K
    7. 104105
    Prev
    Next
    INDEX
    Explanations

    describing change

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

    The neuron detects words and phrases signaling significant change or transformation, such as “shifts,” “change,” “reshaping,” and “undergoing.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    MAXN
    -1.61
    髣
    -1.55
    ྂ
    -1.52
     insuffisamment
    -1.51
    𝙜
    -1.49
    bleshooting
    -1.47
    %),
    -1.43
     subray
    -1.38
    quíni
    -1.38
    VGND
    -1.38
    POSITIVE LOGITS
     how
    2.00
     changes
    1.34
    </h4>
    1.32
     what
    1.29
    𝓒
    1.27
     jaką
    1.26
    欒
    1.23
    ebb
    1.20
    ęż
    1.20
     влади
    1.20
    Activations Density 0.048%

    No Known Activations