© 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. 26723
    Prev
    Next
    INDEX
    Explanations

    I've, it's, they've

    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
    其
    -1.21
     in
    -1.13
     Baie
    -1.00
     by
    -0.99
     vė
    -0.99
     bateria
    -0.98
    Guerra
    -0.96
     classmate
    -0.95
    melada
    -0.94
     pirm
    -0.91
    POSITIVE LOGITS
     my
    2.16
     I
    1.34
     mojej
    1.28
     potência
    1.24
     melhorar
    1.23
     aparência
    1.23
     moż
    1.23
     myself
    1.22
     publicidade
    1.21
     ansiedade
    1.20
    Activations Density 0.038%

    No Known Activations