© 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. 75118
    Prev
    Next
    INDEX
    Explanations

    technical details or components

    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
     they
    -1.05
     collectively
    -1.04
    Élet
    -1.03
     unge
    -1.02
    HasBeenSet
    -0.99
    ighted
    -0.95
    зулта
    -0.94
     staffel
    -0.92
    ֨
    -0.91
     sosi
    -0.90
    POSITIVE LOGITS
     while
    1.31
     its
    1.26
    raujo
    1.06
     if
    1.02
    )--(
    0.96
    herald
    0.93
     itself
    0.91
     in
    0.90
    gencias
    0.88
     przód
    0.88
    Activations Density 0.126%

    No Known Activations