© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100385
    Prev
    Next
    INDEX
    Explanations

    is followed by past participle or not

    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_10/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
     éx
    -1.95
     sesu
    -1.93
     intención
    -1.87
    屨
    -1.87
     bruto
    -1.84
     pauv
    -1.83
    zelfde
    -1.81
     malat
    -1.79
     gordo
    -1.77
     intensif
    -1.75
    POSITIVE LOGITS
    </h2>
    2.11
    ৢ
    2.00
     که
    1.91
     )
    1.90
     That
    1.89
     which
    1.87
     suchen
    1.85
     dritten
    1.81
     którego
    1.71
     to
    1.70
    Activations Density 0.035%

    No Known Activations