© 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. 112215
    Prev
    Next
    INDEX
    Explanations

    get/set methods and variables

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

    method calls to retrieve or access data, particularly using `get` functions or attribute access patterns in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on code tokens that represent function or method calls (e.g. getParam, getAttribute, getExtras, getItem, env, do_action).

    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
     and
    -2.05
     was
    -1.75
     These
    -1.65
     in
    -1.57
     because
    -1.53
     when
    -1.50
     \
    -1.49
     just
    -1.48
     mainly
    -1.47
     we
    -1.45
    POSITIVE LOGITS
     anún
    1.88
    Recently
    1.87
    ኧ
    1.85
    秾
    1.70
    怱
    1.66
    大丈夫です
    1.63
     ayudará
    1.61
    Clearly
    1.61
    ꜆
    1.57
     ofrece
    1.55
    Activations Density 0.015%

    No Known Activations