© 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. 80930
    Prev
    Next
    INDEX
    Explanations

    time ago or back

    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
    陉
    -0.88
    stiker
    -0.81
     quieran
    -0.75
     старый
    -0.75
    painting
    -0.74
    .(*
    -0.73
     embri
    -0.73
    ')['
    -0.72
    墘
    -0.71
     TAMB
    -0.71
    POSITIVE LOGITS
     back
    4.31
    back
    2.58
     назад
    2.55
    Back
    2.44
     ago
    2.39
    BACK
    2.33
     BACK
    2.22
     Back
    2.00
     tillbaka
    1.97
     tilbake
    1.87
    Activations Density 0.019%

    No Known Activations