© 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. 297
    Prev
    Next
    INDEX
    Explanations

    state-of-the-art technologies

    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
    够了
    -1.36
    Laughs
    -1.34
     algemene
    -1.31
     activiteiten
    -1.30
     tijden
    -1.29
    étr
    -1.25
    alucía
    -1.23
     Publicado
    -1.23
     Años
    -1.23
     leerlingen
    -1.23
    POSITIVE LOGITS
     technology
    2.31
     technologies
    2.19
     equipment
    1.95
     advancements
    1.84
     techniques
    1.78
     developments
    1.68
     features
    1.59
     capabilities
    1.51
     technological
    1.47
     いる
    1.43
    Activations Density 0.022%

    No Known Activations