© 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. 22-GEMMASCOPE-RES-131K
    7. 66898
    Prev
    Next
    INDEX
    Explanations

    compliance with

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

    The neuron detects occurrences of the word “compliance.”

    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
    '
    -2.58
     consummate
    -2.47
     They
    -2.47
     několika
    -2.33
     podemos
    -2.28
    aimeJ
    -2.23
     acht
    -2.20
    気づ
    -2.17
    nambuco
    -2.14
    歘
    -2.14
    POSITIVE LOGITS
     古风
    2.55
     キャンペーン
    2.33
     dita
    2.31
    6
    2.28
    ”，
    2.28
    with
    2.28
    yyyy
    2.27
    鞴
    2.27
     sprüche
    2.25
    4
    2.23
    Activations Density 0.022%

    No Known Activations