© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129253
    Prev
    Next
    INDEX
    Explanations

    multiple actions at once

    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
     
    -1.64
     Möglichkeit
    -1.52
    2
    -1.52
     Instead
    -1.51
     entsprechende
    -1.48
     zamiast
    -1.45
     vollständige
    -1.41
     return
    -1.41
     entsprechenden
    -1.37
    いっぱい
    -1.35
    POSITIVE LOGITS
     не
    1.87
     commencé
    1.79
     malheure
    1.71
    Đặc
    1.70
     harika
    1.54
    梣
    1.54
    說
    1.52
     reçu
    1.49
    ff
    1.46
    榦
    1.46
    Activations Density 0.040%

    No Known Activations