© 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. 68489
    Prev
    Next
    INDEX
    Explanations

    determiners followed by quantitative descriptions

    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
     špec
    -1.24
    әне
    -1.23
     uitgenodigd
    -1.20
    𝑧
    -1.14
    kanie
    -1.13
     súčas
    -1.13
     Cedex
    -1.13
     tillegg
    -1.12
    irected
    -1.11
    PLL
    -1.09
    POSITIVE LOGITS
     instituições
    1.36
     businesses
    1.23
     people
    1.23
    cerna
    1.21
     food
    1.21
     vegetation
    1.19
     autorizado
    1.16
     hospitales
    1.16
     foliage
    1.16
     furniture
    1.16
    Activations Density 0.055%

    No Known Activations