© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 854
    Prev
    Next
    INDEX
    Explanations

    Javascript click, submit, blur handlers

    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
     of
    -1.86
     by
    -1.59
     there
    -1.50
     misschien
    -1.41
     aplica
    -1.38
     if
    -1.36
     have
    -1.34
    tahanan
    -1.32
     marca
    -1.32
     去
    -1.28
    POSITIVE LOGITS
    佧
    1.67
     empezó
    1.59
    淠
    1.58
    ícias
    1.55
    </h6>
    1.52
    olving
    1.51
    钐
    1.51
    稣
    1.50
    えると
    1.49
    というわけで
    1.49
    Activations Density 0.012%

    No Known Activations