© 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. 10-GEMMASCOPE-RES-131K
    7. 10088
    Prev
    Next
    INDEX
    Explanations

    fires and burning materials

    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_10/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
     görmek
    -1.37
    存于
    -1.24
    istungen
    -1.23
     schrijven
    -1.21
     atardecer
    -1.21
    腟
    -1.20
    sebagai
    -1.20
    вной
    -1.19
     ditangkap
    -1.16
    做一个
    -1.16
    POSITIVE LOGITS
     quando
    1.20
     andato
    1.08
     punti
    1.07
    coba
    1.06
     النار
    1.02
     other
    1.02
     schermo
    1.02
     deduced
    1.01
     recorded
    1.00
     altre
    1.00
    Activations Density 0.132%

    No Known Activations