© 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. 75213
    Prev
    Next
    INDEX
    Explanations

    reporting speech followed by quotes

    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
     to
    -1.51
     then
    -1.48
     więc
    -1.34
     and
    -1.29
     Some
    -1.24
     in
    -1.23
     Then
    -1.20
     therefore
    -1.18
     also
    -1.15
     than
    -1.15
    POSITIVE LOGITS
     it
    1.63
     “
    1.48
     "
    1.47
     alliés
    1.41
     trajets
    1.38
     jaula
    1.31
     abiye
    1.28
     sièges
    1.27
     ordres
    1.21
     boissons
    1.21
    Activations Density 0.010%

    No Known Activations