© 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. 311
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
     এবং
    -1.05
    aka
    -1.00
    Čo
    -0.99
     '~
    -0.99
     REALLY
    -0.98
    pronounced
    -0.98
    ㍑
    -0.98
     Cette
    -0.97
    ˿
    -0.96
    本当
    -0.96
    POSITIVE LOGITS
     Nadel
    1.01
     you
    1.01
     options
    0.98
     лікар
    0.97
     [
    0.96
     would
    0.93
    śred
    0.93
     acuer
    0.89
    demment
    0.89
    Nomad
    0.88
    Activations Density 0.006%

    No Known Activations