© 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. 93838
    Prev
    Next
    INDEX
    Explanations

    accountant, chartered, auditors

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

    The neuron strongly responds to sequences of uppercase letters (acronyms or section codes).

    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
     CRM
    -0.77
     toxic
    -0.75
    粛
    -0.75
    UKU
    -0.74
     plt
    -0.72
    گرم
    -0.71
     ArrayList
    -0.71
     dé
    -0.71
     alkyl
    -0.71
    campaigns
    -0.71
    POSITIVE LOGITS
     ICA
    1.41
     Chartered
    1.34
     chartered
    1.17
     mercantile
    1.16
     CA
    1.01
    CA
    1.01
     auditors
    0.98
     Auditors
    0.93
     IPCC
    0.93
     ACA
    0.92
    Activations Density 0.008%

    No Known Activations