© 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. 68105
    Prev
    Next
    INDEX
    Explanations

    dates and time periods

    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
    sandal
    -0.99
     eccl
    -0.98
     semacam
    -0.97
     rafraî
    -0.95
     renang
    -0.93
     метра
    -0.89
     mutiara
    -0.88
     pidana
    -0.88
     liburan
    -0.87
     kuiten
    -0.86
    POSITIVE LOGITS
     špec
    1.03
     tých
    1.02
     tohto
    1.01
     voľ
    0.94
     väč
    0.92
     outlook
    0.91
     것이
    0.86
     pomocou
    0.86
     takto
    0.85
     ს
    0.85
    Activations Density 0.032%

    No Known Activations