© 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. 34-GEMMASCOPE-RES-131K
    7. 1264
    Prev
    Next
    INDEX
    Explanations

    java collection types like HashMap

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

    The neuron fires on object‐construction sites in code, especially the “new” operator that instantiates data‐structure objects.

    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
     key
    -1.41
     list
    -1.30
     List
    -1.24
     Map
    -1.22
     Key
    -1.09
    List
    -1.01
     map
    -0.99
    Map
    -0.99
    map
    -0.97
     ArrayList
    -0.96
    POSITIVE LOGITS
    MenuItems
    0.78
    Qualifications
    0.76
    ffen
    0.74
     isotopic
    0.73
    🔛
    0.72
    mitglied
    0.71
    }}/>
    0.71
     שמ
    0.71
     (-)
    0.70
    ricula
    0.69
    Activations Density 0.007%

    No Known Activations