© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33295
    Prev
    Next
    INDEX
    Explanations

    compensation

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

    The neuron activates on occurrences of “compensate” and its morphological variants (e.g. compensation, compensatory, compensated, decompensated).

    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
     Their
    -1.48
    '
    -1.31
     continúas
    -1.29
    同伴
    -1.24
     know
    -1.24
     дополнительных
    -1.23
     incorpora
    -1.22
     nové
    -1.20
    挫折
    -1.20
     reempla
    -1.14
    POSITIVE LOGITS
     églises
    1.41
    获得
    1.29
     COMP
    1.27
    Comp
    1.27
     oreilles
    1.27
     forêts
    1.26
    죠
    1.24
     générations
    1.23
    娥
    1.17
    でしたが
    1.16
    Activations Density 0.050%

    No Known Activations