© 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. 102311
    Prev
    Next
    INDEX
    Explanations

    difficulty and challenges

    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
     verſ
    -1.55
    optimal
    -1.36
     avena
    -1.33
     provoc
    -1.29
     noirs
    -1.26
    겁
    -1.26
    </h3>
    -1.24
    
    -1.22
    迄
    -1.22
    liny
    -1.22
    POSITIVE LOGITS
     Kedua
    1.54
     Siapa
    1.52
     geeigne
    1.46
     consiguiente
    1.46
    says
    1.41
    꽤
    1.41
     ones
    1.38
    のひとつ
    1.38
     IBRARY
    1.37
     każdego
    1.35
    Activations Density 0.056%

    No Known Activations