© 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. 22-GEMMASCOPE-RES-131K
    7. 128731
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
     kic
    -1.22
    ḿ
    -1.09
    recommend
    -1.09
    
    -1.07
    lichten
    -1.06
     recomand
    -1.05
     grátis
    -1.05
     sigui
    -1.04
     ladd
    -1.04
     navigateur
    -1.02
    POSITIVE LOGITS
    れていた
    1.21
     yellow
    1.16
     blue
    1.13
     wykona
    1.05
     group
    1.05
     wcześniej
    1.05
     not
    1.02
     first
    1.02
     wall
    1.01
     green
    1.00
    Activations Density 0.001%

    No Known Activations