© 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. 67320
    Prev
    Next
    INDEX
    Explanations

    asterisk character

    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
     about
    -1.14
     just
    -1.13
     Olímp
    -1.07
     boneco
    -1.05
     now
    -1.05
     eletr
    -1.02
     their
    -1.01
    旅館
    -1.00
     either
    -1.00
     ministres
    -0.99
    POSITIVE LOGITS
    ătoare
    1.16
     comienzos
    1.13
     colecciones
    1.13
     attravers
    1.09
    Gilla
    1.08
     jednak
    1.08
     esercit
    1.05
     impresiones
    1.05
     unserer
    1.04
     však
    1.04
    Activations Density 0.001%

    No Known Activations