© 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. 65006
    Prev
    Next
    INDEX
    Explanations

    continuum, gradient, spectrum, graded

    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
    {
    -1.55
    ↵↵
    -1.36
    hamento
    -1.24
    nya
    -1.20
    formatted
    -1.20
     стороне
    -1.17
                 
    -1.16
     Task
    -1.16
    vábbi
    -1.16
                
    -1.14
    POSITIVE LOGITS
     between
    1.60
     how
    1.53
     these
    1.38
     have
    1.37
     with
    1.35
    between
    1.28
    ᷄
    1.27
     других
    1.26
    both
    1.24
     aprendiz
    1.22
    Activations Density 0.084%

    No Known Activations