© 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. 11287
    Prev
    Next
    INDEX
    Explanations

    may followed by vary, be, or differ

    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
    !
    -1.02
    ↵↵
    -1.00
     out
    -0.99
    ⌀
    -0.94
     just
    -0.94
     robi
    -0.92
    vermectin
    -0.91
     geg
    -0.91
     increment
    -0.91
    ](
    -0.91
    POSITIVE LOGITS
    НИМА
    1.42
     любы
    1.29
     Vitamina
    1.26
    ntä
    1.22
     mikrofon
    1.20
     teilnehmen
    1.17
    attamento
    1.15
     Meksiko
    1.15
    istungen
    1.14
    zlich
    1.14
    Activations Density 0.002%

    No Known Activations