© 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. 1747
    Prev
    Next
    INDEX
    Explanations

    product specifications and attributes

    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
     schreck
    -1.63
     NÃO
    -1.54
    firmasi
    -1.52
    itif
    -1.51
     feind
    -1.50
     nedenle
    -1.48
     joão
    -1.45
     Outros
    -1.45
    が終わ
    -1.45
     Gegner
    -1.45
    POSITIVE LOGITS
     of
    1.91
     as
    1.90
                
    1.79
    1.79
    .
    1.77
     with
    1.66
     in
    1.60
    1.58
         
    1.53
    1.50
    Activations Density 0.075%

    No Known Activations