© 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. 40056
    Prev
    Next
    INDEX
    Explanations

    is a description

    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
     at
    -2.64
     on
    -2.20
     for
    -2.19
     as
    -2.17
     this
    -2.16
     without
    -2.11
     even
    -2.09
     their
    -2.08
     from
    -2.02
     all
    -2.00
    POSITIVE LOGITS
     faciliter
    1.71
     horrid
    1.63
     Dinas
    1.56
     assurent
    1.50
     goofy
    1.50
     刺繍
    1.44
     Atención
    1.44
     dreary
    1.44
     ambiti
    1.43
     créer
    1.39
    Activations Density 0.016%

    No Known Activations