© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103468
    Prev
    Next
    INDEX
    Explanations

    variable assignments =

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

    The neuron strongly activates on user‐defined identifiers (variable, function, and parameter names) in 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
     any
    -1.08
     so
    -1.00
     why
    -0.99
     may
    -0.94
     from
    -0.94
     changes
    -0.93
     some
    -0.91
    +:+
    -0.91
     εφ
    -0.88
     them
    -0.88
    POSITIVE LOGITS
    =
    2.88
     =
    2.58
     = 
    2.02
     $=
    2.00
     $=$
    1.97
    ＝
    1.66
     $=\
    1.66
     }=
    1.64
    =\
    1.57
     }=\
    1.52
    Activations Density 0.012%

    No Known Activations