© 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. 54050
    Prev
    Next
    INDEX
    Explanations

    javascript keywords

    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
     their
    -1.52
    ​=
    -1.42
     belga
    -1.32
    }));
    -1.29
    satunya
    -1.28
     ilustracji
    -1.28
     from
    -1.27
     using
    -1.26
     this
    -1.26
     if
    -1.21
    POSITIVE LOGITS
    Aantal
    1.58
     heridos
    1.48
     detenidos
    1.42
    Tecnología
    1.41
    Ingredienti
    1.34
     giuri
    1.34
     figliu
    1.34
    がありますが
    1.34
    かで
    1.33
    Prijs
    1.32
    Activations Density 0.002%

    No Known Activations