© 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. 10-GEMMASCOPE-RES-131K
    7. 99800
    Prev
    Next
    INDEX
    Explanations

    Ecuador and substrings like "lr"

    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
    
    -3.48
     localizada
    -2.84
     IBOutlet
    -2.84
    
    -2.78
    ཋ
    -2.66
    เกง
    -2.64
    咴
    -2.63
     naturlig
    -2.56
     We
    -2.55
     QtGui
    -2.55
    POSITIVE LOGITS
    ाउनलोड
    2.67
     soo
    2.66
    ra
    2.66
    --"
    2.64
     "
    2.64
     salió
    2.61
    —"
    2.59
     cliché
    2.58
     femeninos
    2.53
    撂
    2.48
    Activations Density 0.001%

    No Known Activations