© 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. 36696
    Prev
    Next
    INDEX
    Explanations

    mixed language identifiers

    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
     our
    -1.55
     жк
    -1.27
     both
    -1.15
     this
    -1.12
    andrea
    -1.10
    })^
    -1.07
     the
    -1.06
    crizione
    -1.05
     eléctricas
    -1.05
    cribing
    -1.04
    POSITIVE LOGITS
     rubio
    1.14
     électro
    1.12
     trent
    1.11
     cannes
    1.07
     Hukum
    1.06
     applau
    1.06
     palma
    1.05
     renova
    1.04
     Diret
    1.03
     romero
    1.03
    Activations Density 0.006%

    No Known Activations