© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128019
    Prev
    Next
    INDEX
    Explanations

    colors and materials

    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
     conflictos
    -1.19
     protestas
    -1.15
     cuando
    -1.12
    脍
    -1.09
     quando
    -1.07
     cuddling
    -1.06
     Atenas
    -1.05
     Monats
    -1.04
     Inhabitants
    -1.04
     utiliza
    -1.03
    POSITIVE LOGITS
     nader
    1.17
    Guns
    1.15
    şağı
    1.13
     nami
    1.11
     dì
    1.10
     militer
    1.09
     classiques
    1.09
    telemetry
    1.09
     accompagner
    1.08
     udang
    1.07
    Activations Density 0.012%

    No Known Activations