© 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. 28635
    Prev
    Next
    INDEX
    Explanations

    words associated with standings

    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
     Políticas
    -1.19
     occafion
    -1.18
    !#
    -1.16
     fubject
    -1.16
     Técnicas
    -1.14
     tokopedia
    -1.13
     fhort
    -1.13
     neceff
    -1.13
    kär
    -1.11
     Prozent
    -1.10
    POSITIVE LOGITS
    </strong>
    1.54
    quirer
    1.52
    secta
    1.27
    ício
    1.27
    </i>
    1.25
    Soorten
    1.25
     治療
    1.19
    asable
    1.18
    1.17
    1.16
    Activations Density 0.022%

    No Known Activations