© 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. 73016
    Prev
    Next
    INDEX
    Explanations

    closing bracket ]

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

    The neuron fires on numeric index expressions in bracketed array- or list-access syntax.

    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
    ſelf
    -1.98
    ają
    -1.95
     scholarly
    -1.87
    🧌
    -1.81
     ancianos
    -1.81
    崀
    -1.73
     strana
    -1.73
     plausible
    -1.70
    He
    -1.70
     threats
    -1.70
    POSITIVE LOGITS
    ]
    2.33
     contribué
    2.11
    й
    1.96
            
    1.94
     办
    1.84
     Also
    1.76
    replyreport
    1.75
     или
    1.74
     очень
    1.73
     なお
    1.71
    Activations Density 0.004%

    No Known Activations