© 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. 34971
    Prev
    Next
    INDEX
    Explanations

    flow passage

    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
    jay
    -0.73
    付いて
    -0.68
     Additive
    -0.68
    crisy
    -0.67
     πι
    -0.66
     Malabar
    -0.65
    Additions
    -0.65
     illiteracy
    -0.64
     signore
    -0.64
     caches
    -0.63
    POSITIVE LOGITS
     Liga
    0.72
    Pc
    0.71
     feuille
    0.69
     respon
    0.68
     Boyer
    0.67
    Occ
    0.67
     Bytes
    0.66
     Dooley
    0.65
    phers
    0.64
     ан
    0.64
    Activations Density 0.037%

    No Known Activations