© 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. 34-GEMMASCOPE-RES-131K
    7. 78498
    Prev
    Next
    INDEX
    Explanations

    employee benefits, rights, training, development, retirement

    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_34/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
     acclaimed
    -1.20
    pushFollow
    -1.15
     обслуживание
    -1.13
     Provides
    -1.12
    上記
    -1.12
    达到
    -1.12
     Umständen
    -1.12
     dilapidated
    -1.12
     momentous
    -1.10
     captivating
    -1.09
    POSITIVE LOGITS
    🥳
    1.27
     who
    1.21
     parachoque
    1.20
    😆
    1.19
     doméstico
    1.19
     cromo
    1.18
    🙋
    1.18
     DIRECTORY
    1.18
     acrílico
    1.16
    😏
    1.16
    Activations Density 0.011%

    No Known Activations