© 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. 11187
    Prev
    Next
    INDEX
    Explanations

    option, method, tag, checked

    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
    óloga
    -1.34
    anwalt
    -1.08
     reno
    -1.06
     predominance
    -1.05
     fave
    -1.04
    Exeunt
    -1.02
     svolta
    -1.02
    Transcripción
    -1.02
     farklı
    -1.01
     juven
    -0.99
    POSITIVE LOGITS
     of
    1.95
     element
    1.59
     aspect
    1.56
     section
    1.53
     you
    1.49
     option
    1.48
     system
    1.48
     algorithm
    1.44
     method
    1.39
     series
    1.38
    Activations Density 0.225%

    No Known Activations