© 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. 1201
    Prev
    Next
    INDEX
    Explanations

    web routing definitions

    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
    ARANCE
    -1.01
     erfüllen
    -0.89
    FromDate
    -0.80
    oubtedly
    -0.79
     besitzt
    -0.76
     酒店
    -0.75
     empfiehlt
    -0.75
     evac
    -0.74
    tragen
    -0.73
     prodigious
    -0.73
    POSITIVE LOGITS
    parameter
    0.88
     robar
    0.87
    に応じて
    0.86
     ACCESS
    0.84
     MINUTE
    0.84
    ží
    0.81
    աքին
    0.81
    grave
    0.81
     parameter
    0.80
     cierra
    0.80
    Activations Density 0.008%

    No Known Activations