© 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. 22-GEMMASCOPE-RES-131K
    7. 104564
    Prev
    Next
    INDEX
    Explanations

    calculus derivatives and integrals

    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_22/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
    blume
    -0.93
    Ｍ
    -0.93
     bereits
    -0.93
     гриб
    -0.92
    已经
    -0.92
     klokken
    -0.92
    пати
    -0.90
     Buhari
    -0.90
     già
    -0.90
     already
    -0.88
    POSITIVE LOGITS
    かったです
    0.88
    thentic
    0.85
     Moser
    0.83
     exhib
    0.82
     distingu
    0.82
     dirigeants
    0.82
     télévis
    0.80
     Occurrence
    0.79
     évidemment
    0.79
    itana
    0.79
    Activations Density 0.010%

    No Known Activations