© 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. 7475
    Prev
    Next
    INDEX
    Explanations

    data structures, tree, map, set, order

    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
    us
    -1.56
    ou
    -1.52
     –
    -1.49
     others
    -1.45
    parseInt
    -1.45
    umerable
    -1.39
    вить
    -1.38
    banez
    -1.38
                    
    -1.35
     Toujours
    -1.35
    POSITIVE LOGITS
     of
    1.80
    '
    1.62
     къде
    1.48
     العالمي
    1.48
     ofreciendo
    1.46
     zamiast
    1.44
     їх
    1.40
    praš
    1.40
     senaste
    1.38
     где
    1.38
    Activations Density 0.023%

    No Known Activations