© 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. 103783
    Prev
    Next
    INDEX
    Explanations

    Premier League, also available

    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
     samego
    -0.90
     makeshift
    -0.88
    </tr>
    -0.83
     silnika
    -0.81
    спонд
    -0.80
    Österreich
    -0.78
    Ironically
    -0.78
     oleju
    -0.77
     Toggle
    -0.75
     mandibular
    -0.75
    POSITIVE LOGITS
     maids
    0.94
     parking
    0.91
    ̂
    0.88
    imon
    0.85
     maid
    0.84
    ensively
    0.84
     Asking
    0.84
    Asking
    0.84
     independente
    0.82
    culate
    0.82
    Activations Density 0.009%

    No Known Activations