© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59225
    Prev
    Next
    INDEX
    Explanations

    Gujarati poet, writer, or critic

    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
    *
    -1.27
    0
    -1.17
     onsdag
    -1.11
    <
    -1.09
     Yo
    -1.08
     feuer
    -1.07
    l
    -1.07
     Ya
    -1.06
     \
    -1.05
     Chairman
    -1.05
    POSITIVE LOGITS
     like
    1.44
     مانند
    1.26
     künf
    1.22
    Eigenschaften
    1.22
     samoz
    1.18
     späteren
    1.16
     beeindruck
    1.16
     Menggunakan
    1.16
    Größe
    1.15
     contributo
    1.15
    Activations Density 0.048%

    No Known Activations