© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103823
    Prev
    Next
    INDEX
    Explanations

    historical and cultural centers

    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
     aprons
    -0.73
     نعم
    -0.71
     advocating
    -0.71
    Amp
    -0.70
    */;
    -0.70
    žem
    -0.69
    וחות
    -0.68
     {});
    -0.68
    renar
    -0.68
    袜
    -0.68
    POSITIVE LOGITS
     medieval
    0.99
     Andalu
    0.97
     Baghdad
    0.96
    tenth
    0.89
     Aver
    0.87
     Medieval
    0.86
     Arab
    0.85
    ǿ
    0.84
     евре
    0.84
     al
    0.82
    Activations Density 0.018%

    No Known Activations