© 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. 36522
    Prev
    Next
    INDEX
    Explanations

    JR codes

    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
     what
    -1.57
     one
    -1.21
     just
    -1.16
     Only
    -1.16
     Even
    -1.15
    what
    -1.12
    What
    -1.11
     it
    -1.09
    Just
    -1.09
    When
    -1.05
    POSITIVE LOGITS
     huéspedes
    1.17
    っていて
    1.00
     cercare
    1.00
     هذا
    1.00
    くらいで
    0.96
    によっては
    0.96
     ingenieros
    0.95
     AppColors
    0.95
    くらいの
    0.94
     tohoto
    0.94
    Activations Density 0.006%

    No Known Activations