© 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. 13018
    Prev
    Next
    INDEX
    Explanations

    JSON object and array structures

    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
     to
    -1.15
     ancora
    -1.08
     for
    -1.02
    licitations
    -1.02
     but
    -0.95
     These
    -0.93
     ۱۶
    -0.92
     alcune
    -0.90
     /(
    -0.90
    médi
    -0.89
    POSITIVE LOGITS
     rempli
    1.07
     result
    1.04
     camiones
    0.99
     paisajes
    0.99
    Kto
    0.98
     lentejuelas
    0.98
     书法
    0.98
    十分的
    0.98
     節
    0.98
     считают
    0.98
    Activations Density 0.009%

    No Known Activations