© 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. 3284
    Prev
    Next
    INDEX
    Explanations

    file paths and URLs

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

    The neuron fires on path-like tokens beginning with “/,” i.e. absolute file or URL paths.

    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
    ESR
    -0.81
     lâu
    -0.78
    𝓮
    -0.77
    kungen
    -0.75
     فأ
    -0.75
     understands
    -0.73
    änger
    -0.71
     come
    -0.69
     kommen
    -0.68
    BuildContext
    -0.68
    POSITIVE LOGITS
     views
    1.06
     ++)
    0.87
    Views
    0.87
     locatie
    0.86
     Views
    0.85
    ⾥
    0.82
    谯
    0.81
    ilish
    0.80
     alugar
    0.78
    ônimo
    0.78
    Activations Density 0.002%

    No Known Activations