© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49585
    Prev
    Next
    INDEX
    Explanations

    articleshow / show

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

    The neuron strongly activates on bits of web-framework code—especially Rails testing and redirect calls (e.g. “test a controller’s create action,” “redirect_to the show action,” etc.).

    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
    AsUp
    -0.73
    Faça
    -0.66
    ert
    -0.65
     Elia
    -0.64
    actic
    -0.64
    viewDid
    -0.64
    ale
    -0.63
    hasError
    -0.63
     الرس
    -0.63
    ILLO
    -0.62
    POSITIVE LOGITS
     show
    7.38
    show
    6.44
    Show
    5.53
     Show
    5.47
     SHOW
    4.75
    SHOW
    4.66
     shows
    3.86
     шоу
    3.48
     showed
    3.17
     Shows
    3.13
    Activations Density 0.119%

    No Known Activations