© 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. 11030
    Prev
    Next
    INDEX
    Explanations

    directory path construction

    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
     desmotiv
    -1.29
     lavadora
    -1.16
     aéreo
    -1.11
     others
    -1.11
    ByPrimaryKey
    -1.10
     parecía
    -1.04
     length
    -1.03
     enseña
    -1.02
     hidratante
    -1.02
     SOBRE
    -1.02
    POSITIVE LOGITS
     województwie
    1.20
     thèmes
    1.07
     comportements
    1.05
    浑身
    1.05
     sogenannten
    1.04
    ITZER
    1.03
     protože
    1.02
    vantaged
    1.02
     Describes
    1.01
    Analyze
    1.00
    Activations Density 0.009%

    No Known Activations