© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10764
    Prev
    Next
    INDEX
    Explanations

    collecting solar energy

    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
    Hvorfor
    -1.27
    みたいに
    -1.17
    الإ
    -1.16
    UEGO
    -1.13
     Leidenschaft
    -1.12
     Lieblings
    -1.09
     stanu
    -1.09
    Jegy
    -1.09
    同上
    -1.08
    Hvem
    -1.08
    POSITIVE LOGITS
    formatie
    1.52
    .
    1.46
     for
    1.34
    ори
    1.31
    middels
    1.29
    реб
    1.29
    fusions
    1.23
    2
    1.18
     These
    1.17
    !
    1.16
    Activations Density 0.204%

    No Known Activations