© 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. 22-GEMMASCOPE-RES-131K
    7. 33521
    Prev
    Next
    INDEX
    Explanations

    accessing object members

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

    The neuron activates on dotted member‐access expressions (object.property or object.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_22/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
     a
    -1.53
    もあり
    -1.14
    などが
    -1.05
    などを
    -1.05
     never
    -1.04
     within
    -0.98
    年は
    -0.98
     mere
    -0.96
    を
    -0.96
    herty
    -0.95
    POSITIVE LOGITS
     manteniendo
    1.14
     verwijzen
    1.13
     beroep
    1.13
     supuestamente
    1.09
    petition
    1.09
     była
    1.07
     disfrutando
    1.06
     beschik
    1.05
     verschil
    1.05
    biendo
    1.05
    Activations Density 0.003%

    No Known Activations