© 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. 22-GEMMASCOPE-RES-131K
    7. 70563
    Prev
    Next
    INDEX
    Explanations

    request and response handling

    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_22/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
     sugi
    -0.90
     lizard
    -0.86
     canción
    -0.79
    parole
    -0.76
    savage
    -0.76
     functie
    -0.76
    edade
    -0.75
     przez
    -0.73
     viņ
    -0.73
     ببین
    -0.72
    POSITIVE LOGITS
    input
    1.05
     input
    1.03
     cuyo
    1.00
     angenommen
    0.98
     submitted
    0.97
    ératures
    0.92
    sowie
    0.88
    getInput
    0.87
     return
    0.86
     remains
    0.84
    Activations Density 0.019%

    No Known Activations