© 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. 34-GEMMASCOPE-RES-131K
    7. 64221
    Prev
    Next
    INDEX
    Explanations

    court orders and opinions

    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_34/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
    地图
    -0.67
    кто
    -0.66
    闵
    -0.66
     Cart
    -0.65
     Hama
    -0.65
    erobic
    -0.63
    Sara
    -0.63
    Hop
    -0.63
     Environmental
    -0.62
     Patri
    -0.62
    POSITIVE LOGITS
     Lifecycle
    0.69
    Anmerkungen
    0.68
     lifecycle
    0.66
     risultati
    0.66
    Blair
    0.66
    軛
    0.65
     NTA
    0.65
     dramatist
    0.63
     स्थिति
    0.63
     Calcul
    0.62
    Activations Density 0.082%

    No Known Activations