© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104670
    Prev
    Next
    INDEX
    Explanations

    Wreck-It Ralph franchise

    np_acts-logits-general · gemini-2.5-flash-lite

    predicting conditions or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    0.48
    ਯ
    0.48
     opposites
    0.47
    ವಿ
    0.46
     exemples
    0.46
    িঝ
    0.45
    ندو
    0.45
    とはいえ
    0.45
    Հ
    0.44
     insights
    0.44
    POSITIVE LOGITS
     Streaming
    0.49
     फॉर्मेट
    0.48
     streaming
    0.46
    约为
    0.46
    hua
    0.44
     SMP
    0.44
    führer
    0.42
     Superman
    0.41
     Gauge
    0.41
     लेबल
    0.41
    Activations Density 0.000%

    No Known Activations