© 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. 60776
    Prev
    Next
    INDEX
    Explanations

    is or are

    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
     quieran
    -1.27
     marquées
    -1.20
     enfrentan
    -1.13
     découver
    -1.09
     connaissent
    -1.07
     знают
    -1.05
    ھا
    -1.04
     commandés
    -1.02
    ントランス
    -1.02
     possiamo
    -1.02
    POSITIVE LOGITS
     are
    5.81
     were
    4.41
     aren
    3.30
     weren
    2.92
     đều
    2.66
     have
    2.64
    are
    2.64
     έχουν
    2.56
     ARE
    2.34
     themselves
    2.30
    Activations Density 0.744%

    No Known Activations