© 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. 34-GEMMASCOPE-RES-131K
    7. 106790
    Prev
    Next
    INDEX
    Explanations

    list manipulation methods like set, add, get

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

    The neuron activates on the period (dot) token used in object-member access or chained method 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_34/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
     initState
    -0.96
     iss
    -0.89
    렛
    -0.81
    IPMENT
    -0.80
    eme
    -0.79
    gp
    -0.79
     Ponce
    -0.79
     tensors
    -0.78
    出场
    -0.78
     幅
    -0.77
    POSITIVE LOGITS
     set
    1.58
    set
    1.27
     remove
    1.12
     Set
    0.94
    Set
    0.91
     removing
    0.89
    设置
    0.89
    remove
    0.88
     removes
    0.87
    セット
    0.81
    Activations Density 0.004%

    No Known Activations