© 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. 80741
    Prev
    Next
    INDEX
    Explanations

    thermal properties and expansion

    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
    irtschaft
    -1.27
     були
    -1.20
     was
    -1.17
     to
    -1.16
     Geheimnis
    -1.13
    意志
    -1.12
     Hvis
    -1.11
    atorial
    -1.10
    endiri
    -1.10
    誅
    -1.09
    POSITIVE LOGITS
     again
    1.23
     selera
    1.20
     dlatego
    1.20
     this
    1.14
     Betrag
    1.12
     entgeg
    1.09
    zubauen
    1.09
    其它
    1.08
     aceste
    1.07
     powinny
    1.07
    Activations Density 0.037%

    No Known Activations