© 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. 22-GEMMASCOPE-RES-131K
    7. 66312
    Prev
    Next
    INDEX
    Explanations

    variable assignments or key-value pairs

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

    The neuron fires on variable identifiers that appear on the left side of an assignment (i.e. names of variables being defined).

    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
     komt
    -1.05
     cantit
    -1.01
    何回
    -0.99
     accett
    -0.93
     definição
    -0.90
     приходит
    -0.89
    ridescent
    -0.89
    carus
    -0.88
    ほとん
    -0.88
    wtf
    -0.88
    POSITIVE LOGITS
     död
    1.13
     minutter
    1.13
    1.09
     includes
    1.03
     that
    1.03
    1.02
    ?>">
    1.02
    1.02
     tæ
    1.01
     février
    1.00
    Activations Density 0.015%

    No Known Activations