© 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. 59569
    Prev
    Next
    INDEX
    Explanations

    Zero Dark Thirty

    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
    ールの
    -0.85
     ווע
    -0.79
     aseguró
    -0.78
     administering
    -0.77
    >);
    -0.76
    Bises
    -0.75
     द्वारा
    -0.75
    讪
    -0.75
    Цита
    -0.74
     Senna
    -0.74
    POSITIVE LOGITS
    Zero
    0.96
     Zero
    0.83
     Prospects
    0.79
    ■
    0.79
    DEP
    0.78
     Zit
    0.77
     Augenblick
    0.76
     zero
    0.75
     ZERO
    0.75
    ZERO
    0.75
    Activations Density 0.011%

    No Known Activations