© 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. 79065
    Prev
    Next
    INDEX
    Explanations

    Symfony and Doctrine

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Tourisme
    -1.05
    marché
    -0.86
    mère
    -0.84
    salomon
    -0.84
     suivante
    -0.84
    Père
    -0.82
    bermuda
    -0.82
    ----</
    -0.82
     Organisateur
    -0.82
     devez
    -0.81
    POSITIVE LOGITS
     Symfony
    1.58
     Doctrine
    1.54
    Doctrine
    1.29
    Symfony
    1.27
     doctrine
    1.24
     twig
    1.09
    doctrine
    1.09
    fony
    1.09
     Sf
    1.05
    choices
    1.02
    Activations Density 0.121%

    No Known Activations