© 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. 48176
    Prev
    Next
    INDEX
    Explanations

    R.layout inflation

    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
     each
    -1.38
     начинает
    -1.36
    hdysval
    -1.33
    breviations
    -1.23
     teñ
    -1.22
    etern
    -1.20
    になりますが
    -1.20
     світу
    -1.19
     और
    -1.16
    ţin
    -1.16
    POSITIVE LOGITS
     of
    1.52
     with
    1.45
    фак
    1.35
     that
    1.24
     вместо
    1.23
    .
    1.20
    様な
    1.20
    Tien
    1.18
     among
    1.17
    ̼
    1.17
    Activations Density 0.007%

    No Known Activations