© 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. 111751
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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
    \
    -2.00
     chileno
    -1.98
     "
    -1.97
    𐑂
    -1.91
     all
    -1.90
     hinder
    -1.89
     обслуживание
    -1.86
    汌
    -1.86
     amplio
    -1.85
     Ganzen
    -1.84
    POSITIVE LOGITS
    ኧ
    2.47
    and
    2.44
     uly
    2.33
     syns
    2.25
    栳
    2.25
    醅
    2.11
     deres
    2.11
     alpes
    2.08
     prate
    1.99
     sels
    1.98
    Activations Density 0.009%

    No Known Activations