© 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. 68248
    Prev
    Next
    INDEX
    Explanations

    XML `rect`, `Gene`, `Field`, `// Copyright`

    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
     of
    -1.20
     one
    -1.16
     found
    -1.13
    而来
    -1.09
     éter
    -1.06
     Arkivert
    -1.06
     porc
    -1.02
     dager
    -1.02
     palma
    -1.02
     veter
    -1.02
    POSITIVE LOGITS
    brtc
    1.16
     deoarece
    1.12
     berbagai
    1.09
     różnych
    1.09
     takich
    1.08
     zahlreichen
    1.08
     verdaderas
    1.07
    athered
    1.06
     wielu
    1.05
     molti
    1.05
    Activations Density 0.000%

    No Known Activations