© 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. 92690
    Prev
    Next
    INDEX
    Explanations

    technical questions and code snippets

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

    The neuron identifies programming‐language code snippets, especially uppercase identifiers and technical terms (e.g. ABAP, OData, convert, data, primitive).

    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
     strategia
    -0.79
    bells
    -0.79
     diskusi
    -0.75
     chanteur
    -0.73
    PLIC
    -0.72
     februari
    -0.72
    ächst
    -0.71
    таратура
    -0.71
    pollo
    -0.71
    cycle
    -0.71
    POSITIVE LOGITS
    mara
    0.81
    connexion
    0.78
     Sei
    0.77
     arbets
    0.77
     table
    0.75
    にゃ
    0.73
     deep
    0.73
    worldwide
    0.71
     særlig
    0.69
    Gue
    0.68
    Activations Density 0.016%

    No Known Activations