© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103762
    Prev
    Next
    INDEX
    Explanations

    compensate for

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

    The main thing this neuron does is detect words that express compensating or counterbalancing actions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ?”
    -2.30
    鴣
    -2.02
    end
    -2.02
    derdag
    -1.99
     contemporanea
    -1.98
     memutus
    -1.95
     generó
    -1.95
     eigener
    -1.90
    ⒋
    -1.90
    目光
    -1.85
    POSITIVE LOGITS
     şi
    2.00
    which
    1.95
    簷
    1.92
    巒
    1.84
    でしたが
    1.84
    ↵
    1.80
    鹩
    1.77
    vidade
    1.74
     และ
    1.73
    是個
    1.73
    Activations Density 0.006%

    No Known Activations