© 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. 34-GEMMASCOPE-RES-131K
    7. 2319
    Prev
    Next
    INDEX
    Explanations

    produced after

    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_34/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
     tamaños
    -1.09
     bocetos
    -1.07
     остальные
    -1.06
     soportes
    -0.95
     spectrophoto
    -0.94
     wszystkie
    -0.93
     последний
    -0.93
     наш
    -0.93
     acabados
    -0.93
    pergillus
    -0.92
    POSITIVE LOGITS
     a
    2.67
     some
    2.11
     an
    2.06
     plenty
    1.73
     considerable
    1.62
     something
    1.58
     significant
    1.54
     additional
    1.51
     substantial
    1.48
     another
    1.45
    Activations Density 0.202%

    No Known Activations