© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130287
    Prev
    Next
    INDEX
    Explanations

    off of / of the

    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
     miserable
    -1.34
     reputable
    -1.34
     decadent
    -1.33
     ruthless
    -1.33
     оборудование
    -1.32
     unimaginable
    -1.30
    ں
    -1.29
     BUT
    -1.28
     disappointed
    -1.28
     consequences
    -1.28
    POSITIVE LOGITS
    //});
    1.57
     Arche
    1.48
     teneur
    1.48
     stderr
    1.41
    например
    1.40
    :${
    1.38
     нѣ
    1.38
     SEAT
    1.38
    isling
    1.37
    ❓
    1.36
    Activations Density 0.031%

    No Known Activations