© 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. 58399
    Prev
    Next
    INDEX
    Explanations

    marriage documents

    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
    mployed
    -1.69
    arthed
    -1.61
     regeringen
    -1.56
     människor
    -1.55
     déchir
    -1.51
     dezelfde
    -1.48
    wyżs
    -1.43
    también
    -1.43
     hendes
    -1.43
     její
    -1.42
    POSITIVE LOGITS
    ’
    1.53
    \\
    1.31
    ↵
    1.31
     иначе
    1.30
     .
    1.29
     the
    1.28
    '
    1.27
     way
    1.27
     in
    1.26
     my
    1.25
    Activations Density 1.055%

    No Known Activations