© 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. 102696
    Prev
    Next
    INDEX
    Explanations

    was/were + past participle

    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
    alucía
    -0.97
     различни
    -0.95
    änner
    -0.92
    while
    -0.89
    ांकि
    -0.87
    LogFactory
    -0.85
    нского
    -0.85
    ншот
    -0.85
    ureusement
    -0.84
    仍
    -0.84
    POSITIVE LOGITS
     seen
    1.38
     among
    1.38
     joined
    1.35
     present
    1.31
     involved
    1.18
     featured
    1.13
     aanwezig
    1.10
     photographed
    1.09
     pictured
    1.05
     shown
    1.05
    Activations Density 0.057%

    No Known Activations