© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116733
    Prev
    Next
    INDEX
    Explanations

    profile and its associated details

    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
    ↵↵
    -1.29
     decidedly
    -1.28
     predominantly
    -1.24
     incredibly
    -1.23
     fabulous
    -1.20
     remarkably
    -1.13
     fantastic
    -1.12
     ridiculously
    -1.12
     exceptionally
    -1.09
     exceedingly
    -1.09
    POSITIVE LOGITS
     jTextField
    1.23
    Shortly
    1.15
    wdriver
    1.13
     fön
    1.13
    EdgeInsets
    1.11
    kelt
    1.11
     campur
    1.09
    鏖
    1.08
    omaly
    1.07
     intricacies
    1.07
    Activations Density 0.015%

    No Known Activations