© 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. 22-GEMMASCOPE-RES-131K
    7. 72853
    Prev
    Next
    INDEX
    Explanations

    click here to find out more

    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
     части
    -1.09
     Total
    -0.96
     certain
    -0.93
     Seven
    -0.91
     –
    -0.91
     main
    -0.90
     Main
    -0.88
     general
    -0.88
     كانت
    -0.87
     broader
    -0.87
    POSITIVE LOGITS
     them
    1.20
     eorum
    1.18
    espère
    1.08
    しくは
    1.08
    ằng
    1.05
    𝗒
    1.03
     potřeb
    1.03
     starts
    1.02
     begins
    1.02
     विश्वसनीय
    1.02
    Activations Density 0.026%

    No Known Activations