© 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. 163310
    Prev
    Next
    INDEX
    Explanations

    year round golf

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

    inflatable or travel pillow

    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
    ర్య
    0.48
     çıkan
    0.45
     معا
    0.44
     heps
    0.44
     interchanges
    0.42
    团
    0.42
    泵
    0.42
    只是
    0.42
    {
    0.41
     ticaret
    0.41
    POSITIVE LOGITS
     Abhishek
    0.54
     who
    0.47
     Lite
    0.47
    0.46
     presence
    0.45
    iradi
    0.45
     Koval
    0.45
     Quanto
    0.44
     Doklady
    0.44
     Loi
    0.43
    Activations Density 0.001%

    No Known Activations