© 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. 92842
    Prev
    Next
    INDEX
    Explanations

    compulsory purchase orders

    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
    ština
    -0.99
     développé
    -0.84
    жается
    -0.84
     retrieval
    -0.82
    ドキドキ
    -0.81
    もとも
    -0.81
    }:{
    -0.80
     < 
    -0.79
    Удачи
    -0.79
     российских
    -0.79
    POSITIVE LOGITS
     scheme
    0.95
     schemes
    0.93
    毅
    0.86
    SCHEME
    0.84
     Scheme
    0.84
     statutory
    0.82
     grants
    0.82
    γχ
    0.80
    Scheme
    0.79
    Ministry
    0.77
    Activations Density 0.016%

    No Known Activations