© 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. 41559
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

    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
    </b>
    -2.05
     に関する
    -1.58
    まずは
    -1.55
     detayl
    -1.52
    ům
    -1.51
     sadece
    -1.48
     mantenga
    -1.48
    						
    -1.42
     تصریح
    -1.41
     reflexive
    -1.40
    POSITIVE LOGITS
     this
    1.98
     you
    1.81
     these
    1.63
    4
    1.50
     people
    1.45
     morally
    1.39
    {
    1.37
     since
    1.34
    hörige
    1.29
    that
    1.28
    Activations Density 0.001%

    No Known Activations