© 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. 28283
    Prev
    Next
    INDEX
    Explanations

    born, made, shot, served, recorded

    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
    ________,
    -1.06
    aminen
    -1.06
     hann
    -1.01
    vermectin
    -1.01
    ridescent
    -0.99
     "-",
    -0.96
     invers
    -0.95
    loans
    -0.93
     telles
    -0.92
     etui
    -0.91
    POSITIVE LOGITS
    es
    0.97
     einer
    0.93
     was
    0.93
     añadir
    0.90
     les
    0.90
     implied
    0.90
     apenas
    0.89
     is
    0.89
     unei
    0.88
     см
    0.85
    Activations Density 0.008%

    No Known Activations