© 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. 71631
    Prev
    Next
    INDEX
    Explanations

    to do

    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
     günstiger
    -1.32
     estacionamiento
    -1.30
    
    -1.30
     anfitrión
    -1.26
     trám
    -1.24
     your
    -1.24
     overzicht
    -1.24
     najwięks
    -1.23
    
    -1.23
     einheit
    -1.22
    POSITIVE LOGITS
     hacerlo
    2.53
     it
    2.28
     doing
    2.22
     melakukannya
    2.20
     do
    1.93
     farlo
    1.78
     does
    1.73
     because
    1.60
     did
    1.55
     ذلك
    1.35
    Activations Density 0.089%

    No Known Activations