© 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. 34-GEMMASCOPE-RES-131K
    7. 99970
    Prev
    Next
    INDEX
    Explanations

    Date Filed:

    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
     freut
    -0.67
    ガジン
    -0.67
     Kao
    -0.65
    റെ
    -0.65
     设备
    -0.62
    మి
    -0.62
     childbirth
    -0.62
     outreach
    -0.61
    みたいです
    -0.61
    雯
    -0.61
    POSITIVE LOGITS
    Implementation
    0.70
    unter
    0.70
     Braunschweig
    0.69
    nová
    0.69
     Обра
    0.69
    Під
    0.69
     implementations
    0.69
    Adder
    0.68
     MONEY
    0.68
     supplements
    0.68
    Activations Density 0.086%

    No Known Activations