© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 286
    Prev
    Next
    INDEX
    Explanations

    arguments used

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

    The neuron fires on tokens belonging to programming‐oriented text (code and config snippets and their keywords), i.e. it flags pieces of code and developer jargon.

    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
    PHOTO
    -0.72
     Adhesive
    -0.71
     Willoughby
    -0.71
    kert
    -0.68
     Pharm
    -0.67
     adhesive
    -0.67
     Rochelle
    -0.67
     stands
    -0.67
     deals
    -0.66
    ///<
    -0.66
    POSITIVE LOGITS
     contacting
    0.81
     Mero
    0.73
     ロング
    0.69
     kontakta
    0.68
    нцип
    0.67
     väg
    0.67
     Rishi
    0.66
    fulness
    0.65
    Conta
    0.65
     säl
    0.65
    Activations Density 0.088%

    No Known Activations