© 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. 73656
    Prev
    Next
    INDEX
    Explanations

    mathematical variable access

    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
     echten
    -1.07
     their
    -1.00
    quiler
    -0.93
     zwanzig
    -0.92
     passenden
    -0.90
     whats
    -0.90
     obud
    -0.90
     czarny
    -0.89
     Оно
    -0.88
     člov
    -0.88
    POSITIVE LOGITS
     galo
    1.08
     paralel
    1.03
     prata
    1.02
     pneu
    1.02
     inov
    1.01
     sonne
    0.99
     remis
    0.98
     eis
    0.98
     islam
    0.97
     ille
    0.96
    Activations Density 0.206%

    No Known Activations