© 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. 10-GEMMASCOPE-RES-131K
    7. 57398
    Prev
    Next
    INDEX
    Explanations

    `is`/`was`/`are` followed by an adjective

    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
     this
    -2.36
     with
    -2.27
     at
    -2.16
     in
    -2.14
     from
    -2.05
     where
    -1.92
     each
    -1.85
     or
    -1.80
     it
    -1.80
     their
    -1.76
    POSITIVE LOGITS
     minimale
    1.78
     abonnement
    1.77
     rechercher
    1.70
     gela
    1.65
     accompagner
    1.65
     eene
    1.64
     fermer
    1.64
     occuper
    1.62
     penser
    1.60
     durer
    1.59
    Activations Density 0.015%

    No Known Activations