© 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. 10-GEMMASCOPE-RES-131K
    7. 42895
    Prev
    Next
    INDEX
    Explanations

    new item creation

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

    The neuron consistently fires on occurrences of the word “new,” marking when something is being created or instantiated.

    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
    )
    -2.23
    .
    -1.97
     a
    -1.85
    torta
    -1.53
    AFN
    -1.52
    southwest
    -1.51
     Ergän
    -1.48
     prohibido
    -1.45
     Erfol
    -1.44
    瑒
    -1.42
    POSITIVE LOGITS
    S
    1.88
    >−
    1.76
    W
    1.75
    4
    1.63
    by
    1.59
     vuotta
    1.55
     with
    1.54
    M
    1.52
     jossa
    1.52
     samh
    1.50
    Activations Density 0.028%

    No Known Activations