© 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. 23922
    Prev
    Next
    INDEX
    Explanations

    way, cause, key, means

    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
     glaubte
    -1.50
     these
    -1.38
     other
    -1.37
    えました
    -1.33
     valgt
    -1.32
     tatuajes
    -1.29
     suche
    -1.29
     there
    -1.29
     personalizadas
    -1.27
     этому
    -1.23
    POSITIVE LOGITS
     his
    1.69
    ^{*}$
    1.56
    }$,
    1.38
    ”,
    1.37
     étant
    1.34
     “
    1.33
    ,“
    1.32
     Moreover
    1.31
     Fünf
    1.30
     Além
    1.30
    Activations Density 0.116%

    No Known Activations