© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93165
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by names and keywords

    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_22/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
     alá
    -1.34
    Результат
    -1.31
    Proses
    -1.31
    itado
    -1.30
     appliquer
    -1.25
     ſon
    -1.24
    
    -1.23
     atrak
    -1.23
     différente
    -1.22
    ឪ
    -1.22
    POSITIVE LOGITS
     ~
    1.07
           
    1.03
     >
    1.02
    ·
    1.02
          
    0.98
    —
    0.97
    /
    0.95
     on
    0.95
     need
    0.94
         
    0.94
    Activations Density 0.018%

    No Known Activations