© 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. 60431
    Prev
    Next
    INDEX
    Explanations

    end of structure

    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
    0
    -1.86
     навіть
    -1.81
     télécommande
    -1.71
    Вот
    -1.70
    是怎么回事
    -1.70
    even
    -1.70
     bahkan
    -1.66
     melaporkan
    -1.63
     даже
    -1.61
     حتی
    -1.61
    POSITIVE LOGITS
     and
    3.09
     or
    2.09
     it
    2.05
    ↵↵
    2.05
     where
    1.70
     is
    1.66
     has
    1.62
     when
    1.53
     such
    1.50
     lichaam
    1.50
    Activations Density 0.002%

    No Known Activations