© 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. 130756
    Prev
    Next
    INDEX
    Explanations

    support access

    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
     to
    -1.72
     EVERY
    -1.51
     ONLY
    -1.48
     for
    -1.48
    =[]
    -1.42
     new
    -1.38
     dilaksanakan
    -1.37
     ALL
    -1.35
     проблеми
    -1.32
     TWO
    -1.31
    POSITIVE LOGITS
     your
    3.02
     you
    2.13
     then
    1.99
    镲
    1.78
     Feuchtigkeit
    1.76
    your
    1.74
     illustratie
    1.72
     ventilación
    1.63
    給你
    1.59
     suministros
    1.59
    Activations Density 0.198%

    No Known Activations