© 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. 66449
    Prev
    Next
    INDEX
    Explanations

    modal or popup windows

    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
     Unterschiede
    -2.00
     avaient
    -1.98
     juzgar
    -1.91
     был
    -1.88
     impresionantes
    -1.86
     denselben
    -1.85
     zwölf
    -1.83
     anstatt
    -1.82
    gucig
    -1.81
     yalnızca
    -1.80
    POSITIVE LOGITS
     nous
    2.20
    \
    2.11
     âme
    1.95
     complé
    1.92
     humbly
    1.91
    我们
    1.91
     traje
    1.88
    藺
    1.86
    悝
    1.84
     étude
    1.77
    Activations Density 0.004%

    No Known Activations