© 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. 85974
    Prev
    Next
    INDEX
    Explanations

    religious songs and hymns

    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
    ’
    -1.42
     eléctrica
    -1.38
    enerbahçe
    -1.35
    ⾒
    -1.33
     slay
    -1.33
    咄
    -1.28
     τε
    -1.27
    𝙳
    -1.26
    lekt
    -1.24
    reté
    -1.23
    POSITIVE LOGITS
     about
    1.72
    mathrm
    1.53
     hunne
    1.48
     Kühlschrank
    1.46
     nuovo
    1.41
     miliardi
    1.35
     OGSÅ
    1.33
     Pantalla
    1.32
     Introducción
    1.31
     of
    1.30
    Activations Density 0.041%

    No Known Activations