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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69143
    Prev
    Next
    INDEX
    Explanations

    names in legal cases

    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
     oscuros
    -1.29
     soucis
    -1.28
    ÑA
    -1.21
    GGLE
    -1.20
    ͑
    -1.20
     trebui
    -1.20
    CLAIMER
    -1.19
    IEVE
    -1.18
     ANOTHER
    -1.16
    ELINES
    -1.16
    POSITIVE LOGITS
     that
    1.77
     by
    1.58
     SqlDbType
    1.55
     those
    1.51
    </em>
    1.48
     not
    1.45
     и
    1.41
     και
    1.41
    Those
    1.38
    That
    1.37
    Activations Density 0.073%

    No Known Activations