© 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. 67856
    Prev
    Next
    INDEX
    Explanations

    family law and courts

    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
     που
    -1.31
     niemand
    -1.28
     można
    -1.27
     mientras
    -1.27
     endeavour
    -1.23
     enquanto
    -1.22
    Ꮋ
    -1.20
    ↵
    -1.16
     Copyright
    -1.16
     endeavors
    -1.15
    POSITIVE LOGITS
    Après
    1.41
    The
    1.30
     this
    1.25
    ㊄
    1.23
    我又
    1.23
    Akhir
    1.21
    Bukan
    1.21
    えると
    1.21
    humanité
    1.20
    GEBUR
    1.20
    Activations Density 0.020%

    No Known Activations