© 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. 22-GEMMASCOPE-RES-131K
    7. 35952
    Prev
    Next
    INDEX
    Explanations

    connectors and combinations

    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_22/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
     utiliser
    -1.21
     célè
    -1.21
     récla
    -1.20
     réserver
    -1.16
     eene
    -1.16
     ralenti
    -1.16
    moderne
    -1.15
     récol
    -1.15
     plafon
    -1.13
     terminer
    -1.12
    POSITIVE LOGITS
     with
    1.43
     at
    1.41
     only
    1.36
     any
    1.30
     more
    1.28
     went
    1.22
     every
    1.20
     other
    1.16
     so
    1.16
     now
    1.16
    Activations Density 0.031%

    No Known Activations