© 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. 58004
    Prev
    Next
    INDEX
    Explanations

    Injectable Component EventEmitter lint

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

    The neuron strongly activates on code‐related identifiers (e.g. class, type, constant, or API names like PyObject, std, Injectable, Generated, EventEmitter), effectively spotting programmer‐defined tokens in source code.

    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
     );
    -1.19
     」
    -1.17
     ){
    -1.10
     』
    -1.07
     }}
    -1.05
     )
    -1.05
     },
    -1.04
     ");
    -1.03
     //
    -1.03
     ),
    -1.00
    POSITIVE LOGITS
    方に
    1.03
     ruso
    0.98
    竄
    0.98
    */
    0.97
    ages
    0.96
    战胜
    0.96
    )
    0.96
     barbarian
    0.94
     使用
    0.94
    哪怕
    0.93
    Activations Density 0.055%

    No Known Activations