© 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. 129310
    Prev
    Next
    INDEX
    Explanations

    expertise and backing

    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
     conferencias
    -1.24
     иллюстрация
    -1.18
     enfermera
    -1.17
     princesas
    -1.13
     avaliar
    -1.05
    lenül
    -1.01
     muñecas
    -1.01
    ="{
    -0.99
     fikk
    -0.97
    ÇA
    -0.95
    POSITIVE LOGITS
     resources
    1.48
     support
    1.24
     expertise
    1.10
     additional
    1.08
     backing
    1.05
     access
    1.04
     rich
    1.03
     powerful
    1.01
     avantaj
    0.99
     wider
    0.99
    Activations Density 0.024%

    No Known Activations