© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102836
    Prev
    Next
    INDEX
    Explanations

    assisted action/reproduction/review/agent/employment/offering

    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
     …..
    -0.98
    ówczas
    -0.96
     imprimer
    -0.95
     handel
    -0.94
     المرجع
    -0.94
    rfan
    -0.92
    ſſen
    -0.91
     of
    -0.91
     complexo
    -0.89
    
    -0.89
    POSITIVE LOGITS
    した後
    1.07
    iyle
    1.02
     témo
    0.94
    了一口气
    0.93
     olika
    0.92
     gezicht
    0.91
     gesprek
    0.90
     hjemmes
    0.88
    ạy
    0.88
    ﺮ
    0.87
    Activations Density 0.271%

    No Known Activations