© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19691
    Prev
    Next
    INDEX
    Explanations

    instantiating objects with new or require

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

    The neuron activates whenever it sees the keyword “new” (i.e. object/instance creation calls).

    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
     initially
    -1.66
     począ
    -1.49
     tych
    -1.40
     zunächst
    -1.40
     environment
    -1.34
     koniec
    -1.34
     originally
    -1.34
     first
    -1.33
     första
    -1.32
    ⩴
    -1.31
    POSITIVE LOGITS
     offrent
    1.23
     fathom
    1.23
    ㆆ
    1.20
     Presiden
    1.19
     dedica
    1.19
    CHREIB
    1.17
     Utiliza
    1.15
    鉏
    1.15
     rivales
    1.13
     Permite
    1.13
    Activations Density 0.007%

    No Known Activations