© 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. 19417
    Prev
    Next
    INDEX
    Explanations

    invest in

    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
    .
    -2.36
    “
    -2.16
     “
    -2.05
     
    -2.03
     we
    -2.00
    7
    -1.91
    @
    -1.89
    ‘
    -1.87
      
    -1.84
    2
    -1.77
    POSITIVE LOGITS
     февраля
    2.03
     nových
    1.97
    viève
    1.91
    amanca
    1.89
    釔
    1.88
     listopada
    1.86
     октября
    1.85
     zijn
    1.81
     étrang
    1.76
    mäßigen
    1.76
    Activations Density 0.007%

    No Known Activations