© 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. 79703
    Prev
    Next
    INDEX
    Explanations

    technical nouns and terms

    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
     construite
    -1.09
     alterar
    -1.05
     inve
    -1.05
    が可能
    -1.03
     obligado
    -1.02
     hones
    -1.01
     étan
    -1.00
     terminée
    -0.98
     lumine
    -0.98
     brou
    -0.96
    POSITIVE LOGITS
     as
    1.11
     at
    1.09
    ensitive
    1.08
     to
    1.07
     in
    1.05
     on
    1.02
     for
    1.02
     hålla
    1.02
     last
    1.01
     nowadays
    1.00
    Activations Density 0.050%

    No Known Activations