© 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. 102040
    Prev
    Next
    INDEX
    Explanations

    places near or outside

    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
    茕
    -1.70
    咵
    -1.69
    Эзоҳ
    -1.52
    菝
    -1.48
    𖣔
    -1.46
    pecified
    -1.45
    :][
    -1.45
    虯
    -1.43
    either
    -1.39
    Ꭳ
    -1.38
    POSITIVE LOGITS
     of
    2.09
     to
    1.73
     before
    1.34
     than
    1.32
     from
    1.27
        
    1.27
     zugel
    1.27
     all
    1.27
     welchem
    1.24
     whom
    1.23
    Activations Density 0.038%

    No Known Activations