© 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. 28384
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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
     női
    -1.07
     męska
    -1.07
     stratég
    -1.04
     krás
    -1.02
    atique
    -0.98
     termé
    -0.97
     なく
    -0.97
     bowiem
    -0.96
     nyelven
    -0.95
    ulence
    -0.94
    POSITIVE LOGITS
     unacceptable
    0.93
    Motorola
    0.91
    莉
    0.82
     عاش
    0.82
     laure
    0.82
    ืม
    0.81
    绣
    0.81
     自
    0.81
     unwanted
    0.79
    Allied
    0.79
    Activations Density 0.006%

    No Known Activations