© 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. 80042
    Prev
    Next
    INDEX
    Explanations

    variable assignment or abbreviation

    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
     vorigen
    -2.27
    悽
    -2.19
    čník
    -2.13
    ない
    -2.09
    ådet
    -2.06
     sánh
    -2.05
     recib
    -2.03
    .
    -2.02
     losers
    -2.00
    끽
    -2.00
    POSITIVE LOGITS
    铪
    3.09
    亖
    2.36
    佧
    2.30
    ཫ
    2.17
    
    2.16
    
    2.05
     odeur
    2.03
     is
    2.03
     {
    1.99
    瑧
    1.99
    Activations Density 0.032%

    No Known Activations