© 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. 22-GEMMASCOPE-RES-131K
    7. 14387
    Prev
    Next
    INDEX
    Explanations

    describing methods and protocols

    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
     правительства
    -1.19
    erals
    -1.17
     harap
    -1.10
     statistik
    -1.10
    ^(@
    -1.08
     maksi
    -1.05
     boya
    -1.05
     akku
    -1.04
     ähnlichen
    -1.04
     kabar
    -1.03
    POSITIVE LOGITS
    رایش
    1.19
     to
    1.19
     steps
    1.10
    מבר
    1.09
     кроссовки
    1.08
    fstream
    1.07
    Measuring
    1.07
    disposing
    1.05
    Hardware
    1.05
    mkdir
    1.05
    Activations Density 0.043%

    No Known Activations