© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    if any

    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_10/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
     niedersachsen
    -1.87
     impe
    -1.86
    
    -1.70
    縢
    -1.69
     dependen
    -1.68
     utilisent
    -1.68
     Austr
    -1.67
     Heu
    -1.65
    踽
    -1.64
    糴
    -1.64
    POSITIVE LOGITS
    россий
    1.80
     THE
    1.79
     you
    1.72
     D
    1.70
    珦
    1.63
     J
    1.60
     On
    1.56
     neuen
    1.56
     H
    1.56
     A
    1.56
    Activations Density 0.006%

    No Known Activations