© 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. 118113
    Prev
    Next
    INDEX
    Explanations

    Madam C.J. Walker, Codd's theorem, worst, Francesco Buzzurro

    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
     on
    -1.17
     sizeable
    -1.07
     at
    -0.96
     with
    -0.95
     Typically
    -0.93
     diverse
    -0.93
     considerable
    -0.91
     sizable
    -0.90
     for
    -0.89
     innovative
    -0.89
    POSITIVE LOGITS
     astonishing
    1.24
     astounding
    1.21
     wonderfully
    1.20
    
    1.19
    鵙
    1.18
     horrid
    1.18
    
    1.16
     amazingly
    1.16
     ridiculously
    1.15
    Neural
    1.15
    Activations Density 0.001%

    No Known Activations