© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 74919
    Prev
    Next
    INDEX
    Explanations

    sequence and time

    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
     doré
    -1.09
     dessins
    -1.09
    
    -1.08
     Portug
    -1.07
     marbre
    -1.06
     ſont
    -1.06
     chien
    -1.05
     compromis
    -1.05
     servis
    -1.05
     manifeste
    -1.05
    POSITIVE LOGITS
     way
    1.59
     ones
    1.52
     thing
    1.51
     one
    1.38
     two
    1.37
     you
    1.34
     I
    1.26
     \
    1.26
     is
    1.24
     only
    1.16
    Activations Density 0.024%

    No Known Activations