© 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. 71739
    Prev
    Next
    INDEX
    Explanations

    coup d'état

    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
    μαστε
    -2.38
     elaborate
    -2.31
    lossians
    -2.27
    姈
    -2.27
     meisten
    -2.19
     examine
    -2.17
    ༀ
    -2.09
    聍
    -2.03
     děti
    -2.03
     był
    -2.00
    POSITIVE LOGITS
     prochains
    2.97
    糴
    2.78
    昳
    2.44
     navires
    2.41
     gesagt
    2.36
     dicono
    2.30
     semblait
    2.27
     avevo
    2.27
     alliés
    2.25
     journées
    2.22
    Activations Density 0.002%

    No Known Activations