© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    programming actions

    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
    ématiques
    -1.84
     versatile
    -1.59
     obtenido
    -1.55
     soothing
    -1.52
     lors
    -1.52
     douleur
    -1.47
     obligado
    -1.47
     getArguments
    -1.45
    呐
    -1.41
     verhalen
    -1.41
    POSITIVE LOGITS
     飾り
    1.61
    anmoins
    1.55
     the
    1.48
    k
    1.48
     mauva
    1.44
     图解
    1.41
     them
    1.41
    ほとん
    1.38
    ſchen
    1.37
     asisten
    1.36
    Activations Density 0.008%

    No Known Activations