© 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. 73665
    Prev
    Next
    INDEX
    Explanations

    well, very, really

    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
    沢山
    -1.66
     Whilst
    -1.48
    Whilst
    -1.38
    Alright
    -1.24
     whilst
    -1.23
     rollercoaster
    -1.23
     dataframe
    -1.19
     McDonalds
    -1.16
     Amongst
    -1.16
    tigten
    -1.13
    POSITIVE LOGITS
     any
    1.23
     gotta
    1.12
     allerdings
    1.12
     instantly
    1.08
    ࠬ
    1.07
     merely
    1.06
     everybody
    1.05
    hynch
    1.05
     accommodating
    1.02
    ᐈ
    1.02
    Activations Density 0.291%

    No Known Activations