© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58371
    Prev
    Next
    INDEX
    Explanations

    SAP application code

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

    The neuron selectively fires on code-like or technical tokens—uppercase identifiers, numbers, and programming keywords—i.e. snippets of code or configuration text.

    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
     Dacia
    -0.85
    ┳
    -0.79
     dachte
    -0.79
    ┻
    -0.75
    جر
    -0.75
     Roch
    -0.75
    ảm
    -0.73
     DCS
    -0.72
     dici
    -0.72
     nóng
    -0.71
    POSITIVE LOGITS
     SAP
    0.92
    }])
    0.84
    ͏
    0.82
    CANCE
    0.81
    lls
    0.80
    ฿
    0.80
     срока
    0.79
    documents
    0.79
     documentos
    0.78
     mana
    0.77
    Activations Density 0.006%

    No Known Activations