© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32638
    Prev
    Next
    INDEX
    Explanations

    recover or restore state

    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
    Negative Logits
     aportar
    -0.95
    Према
    -0.94
     transformación
    -0.93
     Euer
    -0.90
     mudanças
    -0.88
     Veränderung
    -0.87
     poë
    -0.87
    Hauptartikel
    -0.86
     descubrimiento
    -0.86
    Outro
    -0.86
    POSITIVE LOGITS
     from
    2.03
     lost
    1.60
    FromJson
    1.26
     recovers
    1.07
     recovered
    1.07
    fromString
    1.05
    FromString
    1.00
     Restore
    1.00
     restores
    0.99
     losses
    0.98
    Activations Density 0.064%

    No Known Activations